arXiv Query: search_query=(abs:"body shape" OR abs:anthropometric OR abs:anthropometry OR abs:"body measurements" OR abs:"body model") AND (abs:image OR abs:images OR abs:video OR abs:smartphone OR abs:estimation)&id_list=&start=0&max_results=60

Aerial Manipulation in the Wild with Onboard Perception, Policy Learning, and Whole-Body Control

2026-09-24T20:16:38Z

Aerial manipulation in outdoor environments remains challenging due to the simultaneous requirements of reliable state estimation, stable aerial motion, and precise manipulation under external disturbances. In this work, we present a real-world outdoor aerial manipulation framework that integrates imitation learning, onboard LiDAR-inertial state estimation, and whole-body model predictive control. A Diffusion Policy is trained from manipulation demonstrations to generate desired end-effector motions from onboard observations. These learned commands are executed by a whole-body MPC that jointly coordinates the aerial platform and manipulator to realize the desired end-effector trajectory. To eliminate reliance on external motion-capture infrastructure, the platform employs onboard LiDAR-inertial odometry for state estimation during outdoor operation. We validate the complete framework on a physical aerial manipulator and demonstrate successful execution of outdoor manipulation tasks. The experimental results show that demonstration-driven manipulation policies can be effectively integrated with onboard state estimation and model-based whole-body control to enable aerial manipulation beyond controlled indoor environments.

Know Your Body: A Harness for Direct and Self-Improving Robot Control with VLMs

2026-09-22T17:57:19Z

A general-purpose vision-language model can understand a task goal without knowing how a particular robot's motion and functional parts produce the intended effect. We introduce KnowBody, a harness that makes these action-relevant body relations explicit, queryable, and revisable while keeping the model weights frozen. Initialized from one off-task trajectory, a partial body model guides action selection and the interpretation of past interactions. New evidence refines the model, and knowledge dependent on revised body estimates is rechecked before reuse. Across 32 fixed-budget trials on four real-robot tasks, initialized KnowBody achieves 75% completion versus 25% for the native harness and requires fewer planner rounds on successful trials in tasks completed by both. With persistent updates enabled, planner rounds decrease by 29-53% from the first to the fifth recorded success.

Identity-Centric Video Summarization via Hierarchical Fusion of Biometric, Appearance, and 3D Body Features

2026-09-22T08:05:09Z

This work presents a video summarization algorithm based on multi-object tracking and person reidentification. We integrate facial embeddings, 3D body-shape features, and visual appearance into a unified tracking framework. These representations enable hierarchical identity assignment and tracking through bidirectional anchoring, which robustly recovers trajectories under severe occlusion or low visual quality. From these stable trajectories, we generate a compact set of summaries for each identity. We select keyframes using a multi-factor weighting scheme that optimizes biometric clarity, social interaction, and motion dynamics, while Adaptive Non-Maximum Suppression ensures temporal diversity. Evaluation on a custom dataset demonstrates tracking stability, achieving an IDF1 of 97.89% and a MOTA of 95.79%. Compared to Top-K selection, our algorithm also increases visual diversity by 146%, temporal coverage by 89%, and information retrievability by 3.5%.

Locally Private Inference for Riemannian Stochastic Optimization

2026-09-22T21:10:41Z

We develop inference for manifold-valued population minimizers when each observation belongs to a different participant and only locally private messages reach the analyst. The method releases randomized tangent gradients and combines them through Riemannian stochastic approximation and Polyak-Ruppert averaging. Directly inserting a private data surrogate into a nonlinear loss can shift its population target, whereas conditional centring of the released gradient preserves the first-order equation. We introduce symmetric-pair regression (SPR) to estimate the asymptotic variance from the same private messages used for point estimation, without holding out participants or requesting a second release. We prove the central limit theorem and consistency of the fully transcript-based sandwich covariance and intrinsic Wald region under local differential privacy. Simulations across various statistical problems and manifolds support the predicted decrease in estimation error and near-nominal coverage under moderate privacy. An application to NHANES anthropometric data illustrates private estimation of a leading body-size direction and its uncertainty.

Prosthesis-Aware 3D Human Pose Estimation: A Dataset and Benchmark for RSP Users

2026-09-16T09:59:54Z

Recovering 3D human body motion from video is important for applications such as rehabilitation assessment and sports performance evaluation. For prosthesis users, this requires capturing both natural body joints and the geometry of the prosthetic device, a challenge that existing methods are not designed to address. Model-based estimators rely on body models trained on non-amputee individuals and cannot represent prosthesis geometry, while model-free methods lack body kinematic priors and are unreliable under occlusion. This challenge is particularly prominent for users of running-specific prostheses (RSPs), where the RSP has a complex curved geometry and moves dynamically during exercise. To fill this gap, we collect RSP3D, the first 3D dataset of RSP users, covering essential daily-life and exercise actions from participants with varied amputation conditions, using a multi-camera marker-based motion capture setup. We formally define the task of prosthesis-aware 3D pose estimation, evaluate representative methods in a zero-shot setting, and confirm their individual limitations. We further propose a hybrid baseline combining model-based body joint estimation with model-free RSP shape recovery, establishing a starting point for future research.

How Well Do Pseudo-Rigid Body Models Capture Real Plants? In-Field Validation of Simulated Blueberry Canes

2026-09-12T00:40:54Z

Many labor-intensive tasks in fruit production such as pruning require physically interacting with the plant (e.g., pushing, pulling, bending limbs, etc.). Due to increasing labor shortages, there is widespread interest in the adoption of robotics in this area. When the robot must physically interact with the system, a deformable model of the plant is beneficial. Coupled, spring-loaded beams have been used in prior work to build deformable plant models in simulation for learning, planning, and control, but this approach has rarely been validated against the mechanical properties of real-world plants. In this paper, we use this rigid-body model, grounded in real material properties and beam bending theory, to simulate the deformation of blueberry canes under loading. To validate the model, we simulate the canes in MuJoCo and compare their behavior with real-world data collected from probing canes at a commercial farm with a custom testbed. We perform sensitivity analysis on several key modeling variables and show that this approach is highly sensitive to the plant diameter calculations and a priori flexural modulus estimation, which is dependent on season and blueberry variety. We also share our dataset of live blueberry cane deformation, including RGB-D images and measured forces and displacements.

A learning-based joint flow and kinematic state estimation for bodies in highly disturbed flows

2026-09-11T21:55:53Z

Accurate estimation of unsteady aerodynamic flows from sparse measurements remains a fundamental challenge, particularly in the presence of strong disturbances, unknown body kinematics, and incomplete observations. This study presents a data-driven sequential estimation framework for joint reconstruction of unsteady flow fields, aerodynamic loads, and airfoil kinematics from sparse measurements. The approach combines a kinematics-aware nonlinear flow autoencoder with online filtering of streaming measurements. In the resulting reduced-order representation, the forecast and observation operators are learned directly from data, with each forecast-assimilation cycle requiring only a few milliseconds. The framework is evaluated on two-dimensional incompressible flow over an airfoil subjected to random vortical gusts while undergoing arbitrary pitch-up motions. Results demonstrate accurate reconstruction from surface pressure sensors, vertical lines of vorticity sensors, and synthetic velocimetry data with representative shadow regions. The transient informativeness of pressure sensors is quantified through their time-varying contributions to dominant observation modes. While lift is reconstructed from the leading modes, drag, pitch angle, and angular velocity require higher modes. Incorporating limited off-body measurements alongside surface pressure improves observability and reduces estimation error and uncertainty.

Revisiting Avatar-As-Image: High-Fidelity Registration is All You Need

2026-09-10T15:40:39Z

The representation of 3D clothed humans as standardized 2D UV texture and displacement maps over an underlying body model has long been studied. This compact representation is enticing as it enables pretrained image networks to process, generate, and edit 3D avatars, but is only useful if scans are accurately aligned and brought into correspondence via high-fidelity registration. This prerequisite has never been met, which we argue explains the limited quality of prior UV-based methods for clothed humans. Despite its significance, no public method produces high-fidelity SMPL(-X)+D registrations with UV texture from arbitrary clothed scans. We present AvaImg, a multi-stage optimization pipeline, to close this gap: it enforces body-inside-clothing constraint via signed winding numbers, made viable by a three-level efficiency cascade (~10x runtime reduced, ~95% storage saved), and recovers fine surface detail using coarse-to-fine displacement optimization. AvaImg outperforms all baselines in body fitting, shape estimation, and surface registration across six datasets, yielding textured registrations near-indistinguishable from scans (PSNR=34.48dB). For validation of AvaImg's Avatar-as-Image representation as imminently compatible with image foundation models, we auto-encode our UV maps via the frozen FLUX VAE. This achieves only 0.76mm added Chamfer error relative to scan and shows that the resulting maps lie within natural-image distributions, supporting the use of 2D generative priors for 3D avatar generation. Code, data, and Singularity containers will be at https://yuxuan-xue.com/avaimg.

Cross-Model Distillation of a Human-Pose Foundation Model from Unannotated Infant Video for Markerless 3D Pose Estimation

2026-09-01T20:17:00Z

Spontaneous movement is one of the earliest windows onto an infant's neuromotor health, and structured clinical instruments that score it are validated early predictors of cerebral-palsy risk. However, they require specially trained raters, are time-consuming, and carry inter-rater variability. This motivates automated, video-based markerless assessment, especially as marker-based motion capture is impractical in infants. Yet the foundation models that make markerless capture possible are trained almost entirely on adults: our recent multi-view infant study found that no single model is jointly best, with strong 2D keypoint accuracy and direct 3D body recovery split across different models. While that study identifies this trade-off, it does not resolve it. Here, we perform cross-model distillation from the Sapiens 2 pose model into the SAM 3D Body model, using unannotated infant video alone. A frozen teacher supplies dense pseudo-labels, and a differentiable renderer aligns the predicted mesh to them in the training loop. On eleven held-out infants (18 sessions, 173 recordings) under our prior study's multi-view protocol, fine-tuning improves same-view 2D keypoint agreement with the Sapiens reference (median body percentage of correct keypoints @ 10px 0.22 -> 0.42, face 0.22 -> 0.42) and Procrustes-aligned mean per joint 3D position error (25.5 -> 22.2 mm). This demonstrates how cross-model distillation improves SAM 3D Body model performance on infants.

Target-Aware State-Adaptive $p$-Dirichlet Graph Neural Regression for Non-Invasive Body-Composition Estimation

2026-08-30T01:27:28Z

Accurate estimation of body-composition outcomes, including body fat percentage (BFP), bone mineral density (BMD), and appendicular lean mass (ALM), is important for evaluating metabolic, skeletal, and muscular health. Direct assessment using dual-energy X-ray absorptiometry (DXA), however, requires specialized equipment and involves ionizing radiation. We propose a target-aware, state-adaptive $p$-Dirichlet energy-flow graph neural regression ($p$SADE-GNR) framework for estimating these outcomes from non-invasive anthropometric measurements. A neural encoder maps participant representations to hidden states that are propagated over an outcome-specific participant-similarity graph by a state-adaptive forward-Euler discretization of the graph $p$-Dirichlet energy flow. Graph distances weight each original or latent coordinate by its normalized absolute training-fold correlation with the outcome. Using clinical data from the Pennington Biomedical Research Center and five-fold cross-validation, the correlation-weighted model using the original standardized measurements achieved the lowest root mean squared error in all nine primary outcome-cohort combinations and outperformed previously reported support vector regression or least-squares support vector regression reference values in eight of nine comparisons. Autoencoder, variational-autoencoder, and Gaussian-mixture variational-autoencoder representations generally did not improve primary-outcome prediction or reduce computational cost. In an exploratory age-prediction analysis including ALM, BMD, and BFP as predictors, the correlation-weighted GMVAE model achieved the lowest mean error in all three cohorts. These results support target-aware, state-adaptive $p$-Dirichlet graph neural regression for non-invasive body-composition estimation.

Real-Time Musculoskeletal Surrogates for Pediatric Cerebral Palsy: a Credibility Pilot

2026-08-28T14:26:30Z

Real-time musculoskeletal (MSK) surrogates could support personalized rehabilitation for children with cerebral palsy (CP), but their credibility depends on subject-wise evaluation, low inference latency, and calibrated uncertainty. We develop a subject-conditioned causal neural surrogate using OpenSim-derived static parameters, temporal joint kinematics, true muscle capacities, and training-only perturbations. On a real pediatric CP gait dataset comprising nine children, we use leave-one-subject-out validation on six development subjects and evaluate a frozen configuration once on three locked test subjects. The surrogate accurately reproduces musculotendon lengths (R-square = 0.92 in development validation and approximately 0.95 on locked subjects; nRMSE < 8%) while requiring only sub-millisecond to few-millisecond neural inference, well below a 100 ms interactive-rehabilitation target. In contrast, direct muscle-force estimation remains unstable at this small, heterogeneous scale: pooled metrics can overstate within-subject, per-muscle accuracy. A Monte Carlo credibility pilot further shows that propagating only +/-5% anthropometry and muscle-capacity variation produces severely overconfident nominal 90% intervals (approximately 4% force coverage and below 1% MT-length coverage). These results establish a leakage-free evaluation and credibility framework for pediatric MSK surrogates, while identifying force modeling and epistemic uncertainty as the central next challenges for clinically credible digital twins.

Reconstructing Humans and Objects in Interaction using Large Reconstruction Models

2026-08-27T17:35:46Z

Estimation of Human-Object Interactions in 3D (3D HOI) is a fundamental problem in 3D computer vision with applications in AR/VR, robotics, and embodied AI. However, reconstructing these interactions in 3D remains challenging due to depth ambiguities, occlusions, and object shape variability. Existing approaches are primarily concerned with reprojection and contact constraints, fitting parametric human models and object templates to 2D images. In this paper, we explore a different avenue. We present MILO, a framework that leverages the visual capabilities of Large Reconstruction Models (LRMs) to recover detailed 3D human-object interactions from a single image. Our key observation is that LRMs provide a powerful geometric scaffold that preserves relative human-object arrangement and proximity cues. This significantly simplifies the reconstruction procedure, reframing the problem as interpreting the LRM mesh: we segment it into human and object components, fit a parametric body model to the human part, and optionally align an object template to the object part (if such a template is available). MILO achieves strong reconstruction accuracy and outperforms existing baselines across multiple benchmarks and interaction scenarios. Our code is available at https://ac5113.github.io/MILO.

EM Informed Holographic Imaging via Unrolled Deep Networks

2026-09-14T11:51:38Z

Smart Radio Environments (SREs) are a foundational paradigm for the Internet of Everything (IoE), in which dense, phase-coherent antenna arrays form a shared infrastructure for integrated sensing and communication (ISAC). Radio-Frequency (RF) holography is a core sensing building block for SREs: it reconstructs a volumetric map of the electromagnetic (EM) scattering scene from phase-sensitive field measurements, an infrastructural snapshot from stray RF radiation, without dedicated sensors. To make reconstructions accurate and rapidly adaptable, this paper adopts algorithm unrolling, in which the iterations of a classical holographic solver become the layers of a compact, trainable deep network that preserves the EM physical interpretation and learns only a few parameters from limited data. Building on the unrolled Iterative Shrinkage-Thresholding Algorithm (ISTA), namely Learned ISTA (LISTA), this paper first proposes a Weighted LISTA (W-LISTA) that preserves the EM forward model and learns a spatially-varying regularization that steers the sparsity prior towards target shapes consistent with the deployment. Second, the Low-Rank Weighted LISTA (LoRaW-LISTA) applies a low-rank adaptation (LoRa) of the holographic operator to compensate for model mismatch from linearized EM approximations. Both methods are validated on full-wave EM simulations and on a 2.45 GHz indoor campaign with human-body phantoms, improving accuracy and resolution over baselines. Combining the spatially-varying regularization of W-LISTA with the LoRa adaptation of the EM model yields superior reconstruction where classical iterative solvers fail. The proposed tools are rapidly adaptable building blocks for the SRE sensing layer, whose reconstructions, up to body-shape imaging, remain privacy-preserving by design.

Validation of Smartphone-Based Photogrammetric 3D Body Scanning for Automated Anthropometric Measurements Compared with a Commercial Depth-Sensor-Based Body Scanner

2026-08-13T05:00:55Z

3D body scanning has become an important tool in healthcare applications because of its rapid and non-invasive nature. While smartphone-based photogrammetric reconstruction provide a low-cost and accessible alternative to commercial 3D body scanners, their performance for whole-body scanning remains insufficiently validated. Thus, we designed this study to comprehensively validate the photogrammetric 3D scanning application by evaluating automatically extracted whole-body measurements and longitudinal body-shape monitoring. We evaluated a representative application, PolyCam, against the commercial depth-sensor-based Fit3D ProScanner using 144 pregnant participants scanned longitudinally throughout pregnancy. We designed an automatic circumference extraction pipeline to get measurements at four anatomical landmarks from paired 3D scans. A linear mixed-effects model was used to evaluate scanner effects and longitudinal body-shape changes. Measurement consistency was assessed using repeated PolyCam scans and tape measurements on a rigid mannequin. PolyCam demonstrated strong agreement with Fit3D, with average biases below 16 mm, intraclass correlation coefficients above 0.8, and Pearson correlation coefficients above 0.9 across all landmarks. Both systems captured comparable longitudinal body-shape changes. Mannequin experiments showed mean biases below 3.5 mm and no significant differences from tape measurements. These findings support smartphone photogrammetry as a potential accessible alternative to commercial body scanners and applicable for longitudinal 3D body-shape assessment.

Learning human joint torques from pixels

2026-08-10T03:29:48Z

Estimating human joint torques from visual observations is a key step toward bringing biomechanical analysis from controlled laboratories to real-world movement scenarios. Existing torque estimation methods typically depend on surface electromyography, motion-capture markers, force plates, or simulated imitation data, which limits their applicability to ordinary RGB images. In this work, we introduce VID, a vision-based inverse dynamics dataset and benchmark for predicting human joint torques directly from real monocular images. VID contains 63,369 synchronized frames with real human images, kinematic annotations, anthropometric attributes, and OpenSim-derived dynamic labels, providing paired visual and biomechanical supervision for real-image inverse dynamics. We further define a standardized evaluation protocol covering overall torque estimation, joint-specific analysis, and action-specific prediction. To establish a strong reference model, we propose VID-Network, which combines pose-pretrained spatial probabilistic features, marker regression, and temporal torque inference to recover joint torques from image sequences. Experiments on VID show that VID-Network achieves an overall mPJE of 1.7612 N$\cdot$m/kg, improving over the best compared baseline by 39.81\%, and obtains the lowest error across all evaluated joint types and most action categories. VID establishes a first practical benchmark for vision-driven human inverse dynamics and provides a foundation for studying biomechanical inference in less constrained environments.

Sliding Sensors: Configurable Confidence in State Estimation for Continuum Robots

2026-08-05T21:05:25Z

Continuum robots often operate in uncertain environments, where accurate state estimation is essential for safe interactions. Estimate uncertainty is inherently spatially non-uniform: confidence varies depending on where measurements are available. Global estimation accuracy is not always the top priority, but rather achieving sufficient confidence at task-relevant locations along the robot. This extended abstract introduces mechanically reconfigurable sensing enabling uncertainty-shaping in state estimation for continuum robots. We present a concept hardware design demonstrating the feasibility of longitudinal translation of a sensor within a continuum robot. We demonstrate that state estimation confidence can be reconfigured by varying the sensor location, and show a reduction of full-body shape estimation errors when sliding the sensor back and forth over time, compared to a single fixed tip sensor.

Algebraic defect and positive mother body measures

2026-08-03T19:35:09Z

Continuing the study of mother-body measures with algebraic Cauchy transform, we associate with a positive algebraic germ $f$, its irreducible equation $P(z,w)=0$, and a compact convex set $K$ the functional \[ \mathfrak D_{P,K}(μ)= \int_K\left|P\bigl(z,\mathcal C_μ(z)\bigr)\right|^{1/d}\,dA(z), \qquad d=\text{deg}_wP, \] on the set of positive measures supported in $K$ and whose Cauchy transform has germ $f$ at infinity. We prove continuity of $\mathfrak D_{P,K}(μ)$ and attainment of its minimum, characterize zero defect, and obtain the estimate \[ μ(D(a,r))\le C_1r+C_2\mathfrak D_{P,K}(μ)/r \] away from the zero set of the leading coefficient of $P$, where $D(a,r)$ is the disk of radius $r$ centered at $a$. We establish a dual formula for the defect in the rational case and construct positive algebraic Cauchy transforms by Herglotz theory, Fuss--Catalan and Raney laws, positive sums, polynomial pushforwards, and branch graphs. The passage from zero defect to a mother body is made under the planar-null hypothesis of the support.

MHRGait: Gait Recognition from Momentum Human Rig Pose

2026-07-31T07:10:37Z

Gait recognition is shaped by its input representation. Silhouettes encode projected body shape, skeletons encode sparse joint coordinates, and 3D meshes encode dense surface geometry. In each case, identity-bearing articulation is observed through geometric carriers that also vary with clothing, skeletal scale, or body shape. We investigate whether gait can instead be recognized from compact articulated controls. We introduce Momentum Human Rig (MHR) pose as a gait representation, describing each frame using 184 semantically organized body and hand parameters estimated from monocular video. MHRGait groups these heterogeneous controls by anatomy, models their intra-frame coordination and temporal evolution, and produces compact body and hand descriptors. We further introduce MHRGait++, which combines MHR pose with silhouettes through modality-balanced distance fusion, preventing descriptor count from determining modality importance. Experiments on four benchmarks show that MHRGait attains the best overall performance among compared model-based methods on CCPG and SUSTech1K and transfers effectively across datasets, while its recognition network requires only 2.76M parameters and 0.69 GFLOPs for a 30-frame input. MHRGait++ consistently improves silhouette recognizers with a favorable accuracy-efficiency trade-off. These results establish rig-space articulation as an effective standalone gait representation and a complementary cue to projected body shape. Our code is available at https://github.com/duanhuiran/MHRGait.

$^{15}$C inelastic $1/2^+ \rightarrow 5/2^+$ excitation: A single-particle versus a collective process

2026-07-25T17:02:54Z

Background: The excitation of one-neutron halo nucleus $^{15}$C from the $1/2^+$ ground state to the $5/2^+$ first excited state was measured at Argonne National Laboratory by impinging $^{15}$C on a deuterated target at $7.1 A$ MeV. This data was then analyzed in the Distorted Wave Born Approximation using a rigid rotor model for the excitation. Purpose: Being a one-neutron halo, we expect a single-particle excitation to better represent the excitation of $^{15}$C rather than a collective process. We expect the breakup of $^{15}$C to influence the reaction mechanisms because of the low one-neutron separation threshold, which is close in energy to $^{15}$C's first excited state. The goal of this work is to explore various the reaction mechanisms to reinterpret the data of Ref.[1] for the inelastic excitation of $^{15}$C. Method: We solve the scattering problem assuming a three-body model $^{14}$C$+n+d$. We use the Continuum Discretized Coupled Channel method (CDCC) and compare the results with those obtained assuming 1-step DWBA with quadrupole deformation, as done in the original experimental analysis. We also use Bayesian uncertainty quantification to estimate the uncertainties in our predictions coming from the $n$-$d$ interaction. Results: We analyze both the elastic and inelastic angular distributions for $^{15}$C(d,d')$^{15}\text{C}^*$ at $7.1 A$ MeV. Our results show that $^{15}$C breakup effects are important. Conclusions: While CDCC predicts the elastic angular distribution correctly, it is not able to fully describe the experimental inelastic angular distribution. We discuss additional effects that may be responsible for the remaining discrepancy.

Long rigid fibres in a turbulent channel flow: comparison between experiments and simulations

2026-07-21T14:02:10Z

The dynamics of long rigid fibres transported by turbulent channel flow are investigated experimentally and numerically. Experiments use polystyrene fibres of three lengths, $\ell/h=0.25$, $0.5$ and $1$, with moderate inertia, $St^+\approx20$. Their settling velocity is comparable to the friction velocity, causing accumulation near the bottom wall. Measurements are compared systematically with simulations based on a rigid slender-body model. Statistics conditioned on the distance from the wall are used to characterise the effects of fibre length and confinement on translation, orientation and tumbling. Away from the wall, the experimental fibres lag the fluid, with no clear dependence of the velocity deficit on length. Near the wall, the shortest fibres move faster than the local mean flow, whereas longer fibres remain slower, indicating length-dependent sampling of near-wall turbulence. Confinement also strongly constrains orientation and rotation. Fibres close to the wall predominantly undergo "kayaking" motion, tumbling in planes approximately parallel to it. Orientation statistics collapse when wall distance is normalised by fibre length, identifying $y^+/\ell^+$ as the relevant geometrical variable. Where fibres can acquire a significant wall-normal orientation, "pole-vaulting" events produce a local tumbling-rate maximum at $y^+\approx\ell^+/2$. Its magnitude decreases approximately as $(\ell^+)^{-2}$, consistently with a dimensional estimate based on the near-wall velocity variation sampled along the fibre. Experiments and simulations agree well for orientation and tumbling but differ more for translational velocity. The discrepancies highlight the effect of settling, finite fibre thickness and finite slip Reynolds number that are not fully represented by the model.

FlexiAvatar: Unified 3D Gaussian Human Avatars Under Arbitrary Body Visibility

2026-07-21T13:43:31Z

Reconstructing animatable 3D human avatars from monocular video is a fundamental problem in computer vision with broad applications in AR/VR and digital content creation. Existing approaches typically couple parametric body models with neural rendering or 3D Gaussian splatting and optimize all body regions jointly from short videos, which often degrades fidelity in the visible areas. To overcome this limitation, we introduce FlexiAvatar, a unified framework that explicitly optimizes only the visible body regions, effectively eliminating artifacts arising from unobserved limbs. Our method integrates occlusion-robust SMPL-X tracking with part-specific residual refinement to capture high-frequency geometric and appearance details. To complete entirely unseen regions (e.g., back views), we leverage a diffusion-based approach to generate texture consistent with the observed appearance. Experiments on full-body (NeuMan, ZJU-MoCap, WildAvatar), upper/half-body (talk-show clips), and head-only (INSTA) inputs show that FlexiAvatar delivers consistently higher reconstruction quality, outperforming state-of-the-art methods by an average PSNR improvement of approximately 3% across datasets. Finally, by restricting optimization to observed regions, our method reduces the effective number of Gaussians that must be optimized and rendered, leading to reduced runtime and memory overhead in partial-visibility scenarios.

Direct Clinical Joint Angle Extraction from Parametric Body Model Rotation Matrices

2026-07-20T07:47:56Z

Quantitative joint angles are rarely available in routine care because the tools are slow, costly, or confined to a laboratory. We show that clinical joint angles can be read directly from the per-segment rotation matrices a parametric body model already produces, with no inverse-kinematics or musculoskeletal-model fitting step. On the OpenCap LabValidation cohort, using the GEM-X body-model estimator on single-smartphone video, our pooled mean absolute error is 4.50 degrees over the fifteen joint angles that match the OpenCap Monocular reference set, the same accuracy range as OpenCap Monocular's 4.8 degrees on the same cohort and reference standard, from a much simpler pipeline. The step that connects a body model to clinical angles is a small calibration table rather than an optimisation, so the same procedure transfers unchanged to other body models: repeating it on SAM 3D Body, changing only the table, gives 4.66 degrees, statistically indistinguishable from GEM-X, and runs in real time from a live single-camera stream. The method needs no per-recording inputs beyond the video itself: no participant height, no camera-intrinsics database, no per-subject model scaling. This broadens where movement analysis is practical, from in-clinic and at-home recording to telerehabilitation and large-scale decentralised studies.

GalPort: Investigation of the bar in action-angle space

2026-07-08T10:48:57Z

GalPort is a Python package for analysing the orbital dynamics of evolving disc galaxy numerical models in action-angle space. The package implements novel numerical methods for efficiently estimating actions, angles, and frequencies across different, particle-specific timescales: on the scale of radial or vertical oscillation and on the resonant libration/circulation timescale. The algorithm allows calculation of these dynamic quantities simultaneously at all time steps of the simulated galactic evolution. With this tool, one can trace orbital behaviour within time-varying galactic potentials and classify orbits (resonantly trapped, circulating, or passing through a resonance) based on their angle evolution. GalPort also includes specialised options for analysing the phase-space structure of a galactic bar in the disc plane and along its major axis. We demonstrate the package's performance on a typical N-body model of a barred galaxy, obtaining the global distributions of actions and frequencies and performing a detailed orbital decomposition. The code is publicly available under the MIT license at: https://github.com/vdzozulia/galport

Formation of rotating supergiants via stellar mergers in dense clusters: Implications for black hole natal spins

2026-07-06T18:00:01Z

We investigate how massive stellar mergers in young star clusters imprint on black hole spin distributions and the broader implications for gravitational wave sources. The central hypothesis is that angular momentum transferred during stellar mergers substantially affects the spins of the merger products and resulting black holes, with some merger products evolving into collapsar-like objects that retain thick accretion disks that enable efficient spin up. This is in contrast to the more general expectation that black holes form with very small spins, having shed most of their envelope angular momentum via winds and expansion before core collapse. Using roughly 150 N-body models generated with the $\texttt{Cluster Monte Carlo}$ code, $\texttt{CMC}$, we analyze stellar mergers that lead to black hole formation, prioritizing ``significant'' events with mass ratio $q>0.1$. After identifying optimal candidates from our $\texttt{CMC}$ models, we explore detailed stellar structure and post-merger evolution implications with MESA stellar evolution models to capture angular momentum injection and pre-collapse profiles most relevant for the BH natal spin. In our current dataset representative of Milky Way-like globular clusters, up to roughly half of black holes are formed from such mergers, including up to roughly $10\%$ from significant mergers with $q>0.1$. Preliminary angular momentum estimates indicate substantial spin-up during the merger, and trends with mass ratio and stellar properties suggest strong correlations with the final black hole spin. In some cases, dimensionless spin parameters of $a\simeq 0.5$ or more are expected. This process has important implications for the dynamical formation and retention of gravitational wave sources in clusters.

Patient-Specific Articulated Digital Twins from a Single Full-Body CT Scan

2026-09-05T01:34:01Z

Patient-specific anatomical models provide individualized context for surgical planning, image-guided intervention, and algorithm development. However, most CT-derived models are static: they preserve the body configuration captured at scan time, but cannot represent how the same anatomy would appear after patient repositioning. This limitation is especially important for radiographic imaging, where appearance depends jointly on imaging geometry and patient pose. We present a proof-of-concept for constructing a patient-specific \emph{articulated} digital twin from a single full-body CT scan. The method fits a parametric human body model (SMPL) to obtain a patient-aligned kinematic scaffold, binds segmented bones and organs to an anatomy-aware rig, and retargets body-pose changes while preserving skeletal geometry. Using full-body CT scans from three subjects, the fitted scaffold achieved 15.8 $\pm$ 4.0 mm chamfer distance and 95.9 $\pm$ 1.8\% skeletal enclosure. Recomposition at the acquisition pose preserved major radiographic structure, with overall SSIM of 0.872 $\pm$ 0.016 and PSNR of 18.5 $\pm$ 1.4 dB across paired DRRs. Across unseen target poses, the resulting twins enabled articulation while maintaining high skeletal enclosure (94.4 $\pm$ 0.4\%). As a feasibility demonstration, we render the articulated twin as pose-dependent DRRs. These results suggest the feasibility of extending static, view-controllable CT simulation toward pose-controllable anatomical twins for future synthetic imaging and positioning studies.

LUNA: Learning Universal 3D Human Animation Beyond Skinning

2026-09-01T12:24:57Z

Creating photorealistic, animatable 3D human avatars from monocular images still largely depends on Linear Blend Skinning (LBS) and parametric body models, which constrain expressivity and often introduce artifacts due to imperfect fitting. We propose LUNA, an LBS-free universal neural animation model that directly maps multiple 2D controls like images, keypoints, sketches, and unseen characters into 3D Gaussian deformations, bypassing explicit body fitting. At its core, a transformer-based motion regressor disentangles global rigid motion from fine-grained local dynamics to capture both coherent movement and subtle non-rigid effects. To resolve the inherent ambiguity of 2D-to-3D lifting while scaling beyond fitted datasets, we introduce hybrid supervision that distills soft structural priors from an LBS teacher and a loss that supports training on both limited fitted data and large in-the-wild unlabeled videos. Extensive experiments show LUNA achieves competitive visual fidelity compared to LBS-based approaches, while delivering realistic human motion and zero-shot cross-identity generalization across diverse driving modalities. To the best of our knowledge, LUNA is the first end-to-end 3D animatable model that supports implicit 2D driving.

Rethinking the Role of Feature Engineering and Learning Strategies in Few-Shot Hidden Emotion Recognition

2026-06-30T07:25:13Z

In this paper, we present the solution developed by our team, XInsight Lab, which achieved first place in Track 3 of the 4th EI-MIGA-IJCAI Challenge with a test accuracy of 0.76923. To address the challenge of weak and sparse implicit emotion evidence in long videos, this paper extends the winning solution from the previous competition and proposes a compact multi-modal temporal modeling framework. The framework integrates and evaluates the effects of multi-source features, including 2D/3D skeletons, facial expression Blendshapes, DINOv2/v3 vision foundation models, X-CLIP video features, and Gemini semantic priors. Architecturally, we propose a cross-attention mechanism that utilizes static pose features, denoted as Base, as the Query and dynamic micro-motion differential features, denoted as Offset, as the Key and Value. By capturing local relative velocities, this mechanism eliminates static biases related to individual body shape and identity. Concurrently, an adaptive pooling method based on Multiple Instance Learning is employed to extract instantaneous emotions while suppressing background noise in long sequences. Finally, the paper reveals the representation collapse phenomenon of general vision foundation models in micro-dynamic tasks, and analyzes the underlying mechanisms where networks fall into public-leaderboard-driven pseudo-generalization due to shortcut learning and rote memorization.

EMOSH: Expressive Motion and Shape Disentanglement for Human Animation

2026-06-26T12:30:29Z

High-fidelity and expressive controllable human animation is essential for content creation and digital avatar applications. However, existing methods face a dilemma between expressiveness and disentanglement. Mainstream 2D pose-conditioned approaches suffer from "motion-shape entanglement", leading to the leakage of the driving subject's body shape. Conversely, methods relying on 3D priors (e.g., SMPL) achieve geometric disentanglement but struggle to capture facial expressions and complex gestures, resulting in rigid animations. To this end, we propose EMOSH, a novel framework for high-fidelity controllable human video generation. First, an Expressive Human Model (EHM) is introduced as the core control representation. By explicitly disentangling shape and pose parameters, we fundamentally resolve the body shape leakage issue. Alongside this, a robust motion tracker is designed to accurately estimate EHM parameters from video. Second, we propose a Coarse-to-Fine Hybrid Motion Injection strategy, enabling more fine-grained control over expressions and gestures. Furthermore, we introduce a Spatially-Aligned Conditioning mechanism to bridge the domain gap between training and inference, improving identity consistency. Extensive experiments demonstrate that EMOSH outperforms previous methods in both self-driven and cross-driven scenarios, producing high-fidelity videos with vivid expressions while maintaining shape disentanglement.

Lightweight Neural Framework for Robust 3D Volume and Surface Estimation from Multi-View Images

2026-06-22T17:39:18Z

Accurate volume and surface area estimation is critical for diverse applications, from marine ecology to medical diagnostics. However, existing methods often suffer from high computational costs and poor performance with sparse and noisy data. We propose a fully feed-forward framework that regresses scale-normalized volume and surface area and their associated uncertainties directly from multi-view images. By fusing 3D point cloud reconstructions with view-aligned 2D features through a graph-based decoder, our model bypasses iterative optimization, ensuring exceptional scalability and rapid inference. Experimental results demonstrate that our approach outperforms state-of-the-art methods, particularly when operating with a low number of input images. Validated across coral monitoring, dietary analysis, and anthropometry, our proposed framework provides a robust, adaptable solution for quantitative shape analysis. This architecture provides a high-speed, scalable alternative for precise geometric estimation from visual data, maintaining high performance even in resource-constrained or sparse-view scenarios.

Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion

2026-06-19T06:19:29Z

Human motion generation has been widely studied across diverse input modalities, text, music, and video, and recent efforts have unified these into single multimodal frameworks. However, while morphological factors such as gender and body shape are known to produce distinct kinematic signatures, no existing unified framework incorporates this into generation, treating all subjects as morphologically equivalent. We present Odoriko, the first unified multimodal motion generation framework that reflects subject bio-morphological information directly in synthesized motion output. Rather than averaging over subject variation, Odoriko generates motion that is consistent with who is moving, not just what they are asked to do, across text, music, and video conditions within a single model. When explicit morphological information is unavailable, Odoriko additionally recovers subject morphology alongside motion, unifying estimation and generation in one framework. Extensive experiments across text-to-motion, music-to-dance, and video-to-motion benchmarks demonstrate that Odoriko matches or exceeds prior specialized models on standard metrics, while enabling morphology-consistent generation that no existing unified framework supports.

CalTennis: Large Multi-View Tennis Video Dataset and Benchmark of Monocular-to-3D Pose Estimation

2026-06-18T17:52:22Z

The Caltech Tennis Dataset (CalTennis) is a large-scale video benchmark for evaluating monocular-to-3D pose estimation in the wild. CalTennis comprises over 11 million frames (51 hours) of tennis practice and match play from 40 players, captured with 2-6 synchronized cameras at 60 Hz. It is 10 times larger than existing in-the-wild human motion video datasets and 3 times larger than existing MOCAP-ground-truthed datasets, and it is the first large-scale benchmark to provide synchronized multi-view recordings of expert athletic motion. The multi-view setup enables inexpensive, label-free evaluation of monocular-to-3D pose estimation algorithms. We describe a simple, standardized protocol that enables data collection without specialized equipment or expertise, along with fully automated video calibration and synchronization. Benchmarking state-of-the-art monocular-to-3D pose methods on CalTennis, we find that while 3D joint angle recovery is now quite accurate, all models struggle to estimate depth and foot contact consistently. We further propose two novel performance metrics, footwork and stability, as well as qualitatively study body shape inconsistency. These metrics expose previously underexplored failure modes and point to concrete opportunities for improvement in pose estimation and action analysis.

FitVTON: Fit-aware Virtual Try-On via Body-Garment Size Control

2026-06-10T12:40:02Z

While diffusion-based virtual try-on has achieved impressive visual realism, most methods treat the task as 2D inpainting, prioritizing texture preservation over physical plausibility. Consequently, they often produce plausible-looking images that fail to reflect authentic garment fit across diverse body shapes. We present FitVTON, a Fit-aware virtual try-on model on different bodies in the wild. FitVTON encodes garment-body size through structured text prompts, and learn from simulated try-on triplets from parameterized garment model. To improve the fitting effects over garment silhouettes, we introduce two auxiliary head to predict the masks for both the garment and the exposed body. We further introduce a texture rectification stage to improve realistic appearance from simulated data. To evaluate the fitting fidelity, we curate a real-world dataset, FittingEffect3K, combining VLM-based scoring protocol. Both subjective and quantitive experiments show that FitVTON demonstrate authentic fitting fidelity, with significant sizing accuracy and shape preservation over state-of-the-art methods while maintaining competitive image quality. Project Page: https://zenoning.github.io/FitVTON/.

Contactless 3D Human Body Measurement Using Depth Cameras for Smart Health Monitoring

2026-06-10T02:12:34Z

Contactless body measurement technologies are becoming increasingly significant for smart health monitoring, digital health applications, and remote patient assessment. Traditional anthropometric measurements typically necessitate physical contact and trained personnel, which may constrain scalability in remote healthcare settings. In this study, we introduce a depth camera-based framework for estimating human body measurements utilizing 3D point cloud data. An Orbbec Astra 2 depth camera was employed to capture RGB images, depth maps, and 3D point clouds of participants. The captured point cloud was processed using Python-based tools, including Open3D, NumPy, and OpenCV, to segment the human body from the background. Key anthropometric measurements, such as height and arm span, were computed. The measurements were obtained through a combination of spatial filtering and landmark selection on the 3D point cloud, followed by the projection of the computed measurements onto the corresponding RGB image using camera intrinsic parameters. In addition to linear measurements, the approximate body volume and visible surface area were estimated using voxel-based occupancy analysis and mesh-based surface reconstruction methods. The experimental results from a single depth capture demonstrated that accurate body measurements and geometric estimates could be obtained from depth camera data without physical contact. This study provides a foundation for future real-time systems that integrate depth sensing with intelligent health monitoring and generative AI models for smart healthcare applications.

Two-stage imputation of longitudinal anthropometric data with cross-reference harmonisation: a simulation study

2026-06-09T08:41:09Z

Objective. Longitudinal datasets frequently contain missing weight and height measurements, and studies that combine data sources may index measurements against different growth reference standards (e.g., the WHO reference and CDC charts). We describe and evaluate a reproducible two-stage method that imputes missing anthropometry while making the choice of reference standard an explicit parameter. Methods. Stage 1 applies within-subject linear interpolation across visit dates (interior gaps only, no extrapolation). Stage 2 imputes remaining values from an age- and sex-specific growth reference using the LMS method by estimating each subject's centile, carrying it forward and backwards within the subject, defaulting to the 50th centile when a subject is never measured, and reading the expected value off the reference at the visit age. Different references can be supplied per data source so that the standard applied is recorded and auditable. We assessed recovery accuracy by masking and re-imputing a random 20% of observed values. All evaluations used computer-generated synthetic data. Results. On synthetic data (n = 60 subjects, 288 visits, 30% missing), the method resolved missingness to 100% completeness. Masked-value recovery gave a mean absolute error of 1.78 kg for weight (3.5% mean absolute percentage error) and 2.84 cm for height (2.0%), with negligible bias. Values recovered by within-subject interpolation were more accurate than those recovered from the growth reference, as expected, supporting the two-stage ordering. Conclusion. The method offers a simple, dependency-free, and auditable approach to anthropometric imputation, with explicit handling of differing reference standards and per-value provenance. Application to empirical data and propagation of imputation uncertainty into downstream models are the necessary next steps before use in substantive analyses.

From Pixels to Newtons: Predicting In Vivo Joint Contact Forces from Monocular Video

2026-06-04T18:31:00Z

Joint contact forces govern implant longevity, cartilage health, and rehabilitation outcomes, shaping who develops osteoarthritis, who recovers well from joint replacement, and who benefits from biomechanical interventions. Yet they remain measurable only invasively, in a few dozen patients with instrumented implants. I present a physics-free pipeline to predict instantaneous 3D hip and knee contact forces from an uncalibrated monocular video: no markers, force plates, electromyography, subject-specific imaging, or musculoskeletal model. Parametric body meshes are recovered per frame, encoded as kinematic features, and decoded into forces by a transformer whose pose stream is adaptively modulated at every layer by body shape, joint, side, activity text, and self-supervised video tokens (V-JEPA 2), unifying hip and knee in a single model. Under leave-one-subject-out cross-validation across 26 patients and 25 activity categories from the in vivo OrthoLoad database, the pipeline matches the accuracy of subject-specific musculoskeletal simulations ($0.32 \pm 0.08$ BW RMSE for hip; $0.23 \pm 0.03$ BW for knee) and resolves peak force changes smaller than those reported for gait retraining and osteoarthritis progression. Applied zero-shot to an independent instrumented cohort, it rivals or outperforms prior published methods. Even without curated activity labels, video features alone preserve accuracy and enable end-to-end inference on raw footage. Driven by the predictor, a generative motion prior produces biomechanically plausible variants with reduced peak loading, rediscovering strategies from the predictive simulation literature. This pipeline establishes uncalibrated monocular video as a viable modality for estimating joint loading, opening a path toward retrospective analysis of archived clinical recordings, primary-care screening, and at-home rehabilitation tracking.

Hybrid Dynamics Modeling for a Flexible 2-DoF Robotic Arm

2026-06-02T00:12:20Z

This paper examines three approaches for modeling the dynamics of a flexible-link 2-DoF robotic arm to address unmodeled dynamics not captured by rigid-body models. Two physics informed models combine rigid-body dynamics (RBD) formulations with a Gaussian Mixture Model (GMM) to capture residual model errors and linkage flexibility. A kinematics-based regression model serves as a purely data-driven baseline. Using an open-source dataset, torque predictions are first estimated using Ridge regression on kinematic features, while the physicsbased baseline is constructed from published specifications, and ordinary least-squares regression is subsequently used to estimate the same parameter set directly from data. Results show that the physics-based parameters yield the poorest accuracy, while regularized and least-squares estimators align more closely with measured torques. Residual analysis and error metrics highlight the limitations of purely parametric models for flexible-link systems and underscore the value of regularization and data-driven identification, supporting developments of semi-parametric residual learning methods.

How Noisy Poses Break Inverse Dynamics: Analysis and Mitigation for Video-Based Joint Torque Estimation

2026-05-23T23:28:36Z

Recent advances in monocular 3D human pose estimation enable accurate body tracking from video. However, translating these kinematic estimates into physical quantities, such as joint torques, remains challenging due to noise amplification through inverse dynamics. In this work, we provide a systematic analysis of how pose estimation noise propagates through the inverse dynamics pipeline. We present three key findings: (1) pose noise is amplified by approximately 1,000x when computing joint torques via numerical differentiation, (2) proximal joints (spine, hips) are up to 10x more sensitive to noise than distal joints (wrists, hands), and (3) low-pass filtering before differentiation substantially reduces this amplification. To enable this analysis, we develop SMPL-Dynamics, a fully differentiable inverse dynamics module for the SMPL body model that requires no external physics simulators. Our module supports end-to-end gradient computation, and we demonstrate this through differentiable pose refinement, which reduces torque error by 93% with negligible change in pose.

SmoCap: Movement Reconstruction under Morphology-Pose Ambiguity through Unified Scale-Pose Canonicalization

2026-08-19T02:06:07Z

Movement reconstruction pipelines need estimates that support interpretable joint motion and subject morphology, not only low marker fitting error. The same marker fitting error can be explained by different mixtures of morphology and posture, while weakly observed degrees of freedom are not uniquely identifiable, yielding anatomically inconsistent yet numerically acceptable solutions. We present SmoCap, a unified scale-pose framework that resolves morphology-posture ambiguity while preserving coordinated motion under weak observability. SmoCap solves a constrained trust-region QP with analytical proxy-mapped pose and scale Jacobians. Under matched observations, SmoCap is compared with an established OpenSim baseline using fluoroscopy-derived knee motion and anthropometric ground truth as external references. Extreme yoga sequences further probe coordinated spine motion under weak observability. In the controlled comparison, the OpenSim baseline achieved lower marker RMSE (8.81 vs 19.14 mm), whereas SmoCap achieved lower knee-orientation RMSE against fluoroscopy (5.82 deg vs 7.50 deg) in 24 of 28 trials and all six subjects. Mean absolute anthropometric endpoint errors were 8.44 vs 9.51 mm on CAMS-Knee and 6.87 vs 8.77 mm on Riglet for SmoCap and OpenSim, respectively. Proxy coupling preserved expressive and coordinated spine motion with marginal fitting error increase (+0.14 mm, +0.6%) in the yoga ablation. Median runtime was 0.204-0.332 ms/frame, with consistently 2-3 iterations. Marker RMSE alone did not reliably indicate better motion or morphology recovery. SmoCap instead combines unified scale-pose estimation with proxy coordination. It achieved lower motion and morphology errors in the external evaluations while supporting weak-observability-aware, cohort-scale movement reconstruction for downstream pipelines that depend on interpretable subject motion and morphology.

Beyond Model Readiness: Institutional Readiness for AI Deployment in Public Systems

2026-05-17T00:11:09Z

Many public-sector artificial intelligence systems fail not at the point of model development, but at the point of deployment. Systems that perform well in internal testing may still stall because the receiving institution lacks the approvals, data arrangements, human oversight, operational capacity, fiscal continuity, or legal clarity needed for broader rollout. Existing responsible AI and model evaluation frameworks are valuable, but they primarily assess models, datasets, and developer-side processes, not the readiness of the institution that must use the system in practice. We introduce Institutional Alignment Readiness (IAR), a five-dimensional framework for assessing deployment readiness in public systems. The framework is designed for resource-constrained settings, where gaps between technical viability and responsible deployment are most acute. It is grounded in two anonymized operational cases from a large public education system: an image-based anthropometric screening tool and a speech-analysis system for early learning risk identification. Both reached technically viable stages but could not advance to broader rollout for institutional rather than technical reasons. We use these cases to motivate a practical readiness framework covering institutional and operational compatibility, data ecosystem maturity, human oversight capacity, fiscal sustainability, and regulatory alignment readiness. IAR is designed to complement, not replace, established AI evaluation tools. It assesses the receiving institution rather than the artifact alone and supports staging decisions such as no-go, pilot-only, or readiness for broader deployment.

GaitProtector: Impersonation-Driven Gait De-Identification via Training-Free Diffusion Latent Optimization

2026-05-12T17:27:56Z

Conventional gait de-identification methods often encounter an inherent trade-off: they either provide insufficient identity suppression or introduce spatiotemporal distortions that impede structure-sensitive downstream applications. We propose GaitProtector, an impersonation-driven gait de-identification framework that formulates privacy protection as a unified objective with two tightly coupled components: (i) obfuscation, which repels the protected gait from the source identity, and (ii) impersonation, which attracts it toward a selected target identity. The target identity serves as a semantic anchor that biases optimization toward structurally plausible gait patterns under the pretrained diffusion prior, helping preserve dominant body shape and motion dynamics. We instantiate this idea through a training-free diffusion latent optimization pipeline. Instead of retraining a generator for each dataset, we invert each input silhouette sequence into the latent trajectory of a pretrained 3D video diffusion model and iteratively optimize latent codes with a differentiable adversarial objective to synthesize protected gaits. Experiments on the CASIA-B dataset show that GaitProtector achieves a 56.7% impersonation success rate under black-box gait recognition and reduces Rank-1 identification accuracy from 89.6% to 15.0%, while maintaining favorable visual and temporal quality. We further evaluate downstream utility on the Scoliosis1K dataset, where diagnostic accuracy decreases only from 91.4% to 74.2%. To the best of our knowledge, this work is the first to leverage pretrained 3D diffusion priors in a training-free manner for silhouette-based gait de-identification.

Egocentric Whole-Body Human Mesh Recovery with Prior-Guided Learning

2026-05-09T01:59:01Z

Egocentric human mesh recovery (HMR) from monocular head-mounted cameras is increasingly important for AR/VR applications, but remains challenging due to the lack of reliable ground-truth (GT) annotations based on parametric human body models such as SMPL and SMPL-X for real egocentric images. Existing egocentric HMR methods typically rely on pseudo-GT and focus on body pose estimation, which limits their ability to recover fine-grained whole-body details such as hands and face. We study egocentric whole-body human mesh recovery and propose a prior-guided learning framework that reconstructs whole-body meshes from a single egocentric image. We construct more accurate optimization-based pseudo-GT aligned with 3D joint supervision, and leverage multiple priors by adapting an exocentric HMR foundation model together with a diffusion-based pose prior. A deterministic undistortion module is further adopted to handle fisheye distortions in egocentric images. Experiments across multiple egocentric benchmarks demonstrate improved whole-body reconstruction compared to state-of-the-art methods, and show that our optimization-based pseudo-GT is substantially more accurate than existing regression-based pseudo-GT. To facilitate reproducibility, the code and dataset annotations are publicly available at https://github.com/naso06/EgoSMPLX.

Non-intrusive Body Composition Assessment from Full-body mmWave Scans

2026-05-25T12:04:26Z

Body composition assessment (BCA) provides detailed information about the distribution of different tissue types in the body, enabling more precise characterization of individuals than BMI or weight alone. Consistent and frequent BCA would be valuable for personalized medicine, but the gold standard methods for BCA, such as CT and MRI, are only practical for opportunistic monitoring of patients with clinical indications for imaging and are not suitable for routine use in the general population. Here, we consider an imaging modality which is not currently used in medical applications: millimeter wave (mmWave) radar. Commonly used in security settings, mmWave scans enable fast, non-intrusive, and privacy-preserving reconstruction of full body shape without the need to remove clothing. To demonstrate the feasibility of fast and convenient BCA from mmWave scans, we present a method for BCA value regression using a multi-task learning strategy that leverages synthetic mmWave-like point clouds derived from clinical imaging and parametric human models. We evaluate the model on a pilot cohort of real mmWave scans with bioimpedance-derived body fat measurements, supporting the feasibility of estimating VAT and body fat percentage (BFP) from mmWave data acquired through clothing in a standing posture. We find that the model can predict VAT and BFP with a mean absolute error of 1.0 L and 3.2%, respectively, demonstrating the potential of mmWave scanning for routine BCA in a wide range of settings.

Exploring Clustering Capability of Inpainting Model Embeddings for Pattern-based Individual Identification

2026-05-06T13:33:14Z

In this paper, we explore deep learning techniques for individual identification of animals based on their skin patterns. Individual identification is crucial in biodiversity monitoring, since it enables analysis of decline or growth of populations, or intra-species interactions within populations. Models trained for the task of individual identification often do not focus on the skin pattern of animals, but on background details or body shape details. These characteristics are not individually specific, or can change drastically through time. We focus on techniques that will make machine learning models more responsive to skin pattern structure when extracting individual visual embeddings from images. For this, we explore image inpainting of task-specific masks as an auxiliary task to enhance ML-based individual identification from animal skin patterns. We propose a comparative analysis among four models as an encoder backbone for the individual identification task. We focus on the case study of zebrafish, which is a widely recognized biological model organism, and which exhibits individually identifying skin patterns. To evaluate encoder backbone performance, we present standard metrics for classification accuracy, embedding clustering metrics, and GradCAM visualizations.

OPENJ: A Conceptual Framework for Open-Source Digital Human Modeling and Ergonomic Assessment in a CAD Environment

2026-05-05T20:04:46Z

Industrial workplace challenges range from musculoskeletal disorders -- a leading cause of occupational injury -- to suboptimal workstation layouts, inefficient task sequences, and poor human-equipment fit. Digital human modeling (DHM) tools address several of these challenges by placing a scalable virtual mannequin in a computer-aided design (CAD) environment, enabling engineers to evaluate ergonomic risk through standardized assessment methods (RULA, REBA, NIOSH Lifting Equation, OWAS), optimize workstation layouts for reach and visibility, predict task postures through inverse kinematics, and simulate operations before physical implementation. Despite four decades of development since the Jack system originated at the University of Pennsylvania in the 1980s, the integrated DHM capability set -- anthropometric mannequin, posture prediction, ergonomic assessment, and CAD integration -- remains exclusive to commercial platforms such as Siemens Tecnomatix Jack (Process Simulate), Dassault DELMIA, Humanetics RAMSIS, and the University of Iowa's Santos system. These platforms operate under proprietary, vendor-quoted pricing models, and their acquisition and operating costs, together with closed-source implementations, have been repeatedly identified as practical adoption barriers for individual researchers, small-to-medium enterprises, and educational institutions. Organizations without access resort to manual observational methods -- paper-based worksheets applied to photographs or video -- sacrificing the predictive power and reproducibility that computational analysis provides. The paper serves as a design blueprint for (OpenJane/Joe), positioning the project for subsequent open-source implementation and community adoption.

Multimodal synthesis of MRI and tabular data with diffusion in a joint latent space via cross-attention

2026-05-05T08:30:20Z

We propose a multimodal latent diffusion model that jointly synthesizes volumetric magnetic resonance imaging (MRI) and tabular clinical data within a shared latent space via cross-attention. This approach enables coherent joint representation learning of MRI and tabular modalities for generative modeling. Our model utilizes a variational autoencoder to fuse the two modalities before diffusion-based synthesis, allowing modality-appropriate reconstruction with separate decoders for MRI and tabular data. We evaluated the framework on data from the German National Cohort (NAKO Gesundheitsstudie), comprising over 10,000 participants with MRI scans and clinical tabular features such as age, sex, body measurements, and ethnicity. The generated MRI volumes exhibited anatomical plausibility and body composition consistent with the synthesized tabular attributes. Quantitative evaluation using Fréchet distance and precision-recall metrics confirmed high-fidelity image generation. In the tabular modality, our model outperformed CTGAN across standard evaluation metrics and achieved results comparable to TVAE, demonstrating competitive performance relative to established unimodal baselines. This work is, to our knowledge, the first to demonstrate the feasibility of jointly modeling MRI and mixed-type tabular data in a single latent diffusion framework, offering a proof-of-concept for generating coherent synthetic multimodal patient data and aligning with the broader goal of developing digital twins in healthcare.

Gait Recognition via Deep Residual Networks and Multi-Branch Feature Fusion

2026-04-30T03:09:51Z

Gait recognition has emerged as a compelling biometric modality for surveillance and security applications, offering inherent advantages such as non-intrusiveness, resistance to disguise, and long-range identification capability. However, prevailing approaches struggle to comprehensively capture and exploit the rich biometric cues embedded in human locomotion, particularly under covariate interference including viewpoint variation, clothing change, and carrying conditions. In this paper, we present a high-precision gait recognition framework that deeply extracts and synergistically fuses gait dynamics with body shape characteristics through a multi-branch architecture grounded in deep residual learning. Specifically, we first employ the High-Resolution Network (HRNet) to perform robust skeletal keypoint estimation, preserving fine-grained spatial information even under low-resolution inputs. We then construct three complementary feature branches -- body proportion, gait velocity, and skeletal motion -- from the extracted pose sequences. A 50-layer Residual Network (ResNet-50) backbone is leveraged within a deep feature extraction module to capture hierarchically rich and discriminative representations. To effectively integrate heterogeneous feature streams, we design a Multi-Branch Feature Fusion (MFF) module inspired by channel-wise attention mechanisms, which dynamically allocates contribution weights across branches through learned activation parameters. Extensive experiments on the cross-view multi-condition CASIA-B benchmark demonstrate that our method achieves a Rank-1 accuracy of 94.52\% under normal walking, with the best recognition performance among skeleton-based methods for the coat-wearing condition.

IAM: Identity-Aware Human Motion and Shape Joint Generation

2026-04-28T03:15:12Z

Recent advances in text-driven human motion generation enable models to synthesize realistic motion sequences from natural language descriptions. However, most existing approaches assume identity-neutral motion and generate movements using a canonical body representation, ignoring the strong influence of body morphology on motion dynamics. In practice, attributes such as body proportions, mass distribution, and age significantly affect how actions are performed, and neglecting this coupling often leads to physically inconsistent motions. We propose an identity-aware motion generation framework that explicitly models the relationship between body morphology and motion dynamics. Instead of relying on explicit geometric measurements, identity is represented using multimodal signals, including natural language descriptions and visual cues. We further introduce a joint motion-shape generation paradigm that simultaneously synthesizes motion sequences and body shape parameters, allowing identity cues to directly modulate motion dynamics. Extensive experiments on motion capture datasets and large-scale in-the-wild videos demonstrate improved motion realism and motion-identity consistency while maintaining high motion quality. Project page: https://vjwq.github.io/IAM

OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Prediction

2026-04-23T11:55:19Z

Fitting an underlying body model to 3D clothed human assets has been extensively studied, yet most approaches focus on either single-modal inputs such as point clouds or multi-view images alone, often requiring a known metric scale. This constraint is frequently impractical, especially for AI-generated assets where scale distortion is common. We propose OmniFit, a method that can seamlessly handle diverse multi-modal inputs, including full scans, partial depth observations, and image captures, while remaining scale-agnostic for both real and synthetic assets. Our key innovation is a simple yet effective conditional transformer decoder that directly maps surface points to dense body landmarks, which are then used for SMPL-X parameter fitting. In addition, an optional plug-and-play image adapter incorporates visual cues to compensate for missing geometric information. We further introduce a dedicated scale predictor that rescales subjects to canonical body proportions. OmniFit substantially outperforms state-of-the-art methods by 57.1 to 80.9 percent across daily and loose clothing scenarios. To the best of our knowledge, it is the first body fitting method to surpass multi-view optimization baselines and the first to achieve millimeter-level accuracy on the CAPE and 4D-DRESS benchmarks.

Rings Around Non-Spherical Worlds: Sub-mm Dust Retention Around Triaxial Small Bodies in the Solar System

2026-04-14T19:06:13Z

We investigated the millennial-scale evolution of narrow innermost rings composed of pebble-sized to sub-millimeter particles around the four known ring-bearing small bodies Chiron, Chariklo, Quaoar, and Haumea. Using a GPU-accelerated 8th-order Hermite integrator, we modeled the combined effects of solar radiation pressure (RP), shadowing of the rings by the host body, heliocentric motion, and the non-axisymmetric gravitational field of the rotating triaxial central body. The calculations compare spherical and triaxial-body models, as well as coplanar and inclined ring configurations. In spherical models, solar RP excites particle eccentricities, leading to accretion onto the central body above a critical RP parameter. This effect is strongest for the lower-mass systems, Chiron and Chariklo, where particles with relatively modest radiation forcing are rapidly removed. In contrast, when the triaxial shape of the host body is included, rapid apsidal precession suppresses RP-driven eccentricity growth and prevents material loss from the ring over the simulated interval. The triaxial models also suppress the previously identified Sun-facing reorientation of highly inclined rings and instead produce moderate vertical broadening. Strongly confined rings persist for RP parameters corresponding to particle sizes larger than about 7-40 micrometers, depending on composition. Their characteristic radial widths are about 10 km for Chiron and Chariklo and about 40-70 km for Quaoar and Haumea. The vertical thicknesses of the rings are estimated to be on the order of 1 km for Chiron and Chariklo, and only several hundred meters for Quaoar and Haumea. Our results suggest that narrow rings around triaxial small bodies in the Solar System can plausibly retain sub-millimeter particles over dynamically relevant timescales shorter than Poynting-Robertson drag.

Real-Time Human Reconstruction and Animation using Feed-Forward Gaussian Splatting

2026-07-23T17:36:45Z

We present HumanGS, a generalizable feed-forward Gaussian splatting framework for human 3D reconstruction and real-time animation from sparse multi-view RGB images and their associated SMPL-X poses. Unlike prior methods that rely on depth supervision, fixed input views, UV maps, repeated feed-forward inference for each target pose or view, or computationally expensive vertex-to-image cross-attention, HumanGS employs a simple transformer architecture that explicitly associates SMPL-X vertices with multi-scale image features through geometric back-projection. This eliminates the need for large pre-trained human representation models while naturally aggregating complementary information from multiple views. The aggregated vertex features are mapped by a lightweight MLP decoder to a canonical set of 3D Gaussian primitives aligned with SMPL-X vertices. One Gaussian is regularized to remain close to the SMPL-X surface, providing a strong geometric prior and stable correspondence to the parametric body model, while a small set of unconstrained Gaussians per vertex captures geometric details beyond the body surface, such as clothing and hair. The resulting canonical representation is animated efficiently using linear blend skinning and Gaussian rasterization without further network inference. Trained entirely from scratch on only 10K frames from THuman2.1, HumanGS achieves reconstruction quality comparable to or better than state-of-the-art methods while reducing reconstruction time by over 15 times compared to recent transformer-based approaches, enabling real-time animation and interactive applications. Code and pre-trained models are available at https://github.com/Devdoot57/HumanGS .

RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild

2026-04-08T17:48:46Z

Scaling up robot learning will likely require human data containing rich and long-horizon interactions in the wild. Existing approaches for collecting such data trade off portability, robustness to occlusion, and global consistency. We introduce RoSHI, a hybrid wearable that fuses low-cost sparse IMUs with the Project Aria glasses to estimate the full 3D pose and body shape of the wearer in a metric global coordinate frame from egocentric perception. This system is motivated by the complementarity of the two sensors: IMUs provide robustness to occlusions and high-speed motions, while egocentric SLAM anchors long-horizon motion and stabilizes upper body pose. We collect a dataset of agile activities to evaluate RoSHI. On this dataset, we generally outperform other egocentric baselines and perform comparably to a state-of-the-art exocentric baseline (SAM3D). Finally, we demonstrate that the motion data recorded from our system are suitable for real-world humanoid policy learning. For videos, data and more, visit the project webpage: https://roshi-mocap.github.io/

Better Rigs, Not Bigger Networks: A Body Model Ablation for Gaussian Avatars

2026-04-03T00:26:23Z

Recent 3D Gaussian splatting methods built atop SMPL achieve remarkable visual fidelity while continually increasing the complexity of the overall training architecture. We demonstrate that much of this complexity is unnecessary: by replacing SMPL with the Momentum Human Rig (MHR), estimated via SAM-3D-Body, a minimal pipeline with no learned deformations or pose-dependent corrections achieves the highest reported PSNR and competitive or superior LPIPS and SSIM on PeopleSnapshot and ZJU-MoCap. To disentangle pose estimation quality from body model representational capacity, we perform two controlled ablations: translating SAM-3D-Body meshes to SMPL-X, and translating the original dataset's SMPL poses into MHR both retrained under identical conditions. These ablations confirm that body model expressiveness has been a primary bottleneck in avatar reconstruction, with both mesh representational capacity and pose estimation quality contributing meaningfully to the full pipeline's gains.

Learning a dynamic four-chamber shape model of the human heart for 95,695 UK Biobank participants

2026-03-30T17:28:39Z

The human heart is a sophisticated system composed of four cardiac chambers with distinct shapes, which function in a coordinated manner. Existing shape models of the heart mainly focus on the ventricular chambers and they are derived from relatively small datasets. Here, we present a spatio-temporal (3D+t) statistical shape model of all four cardiac chambers, learnt from a large population of nearly 100,000 participants from the UK Biobank. A deep learning-based pipeline is developed to reconstruct 3D+t four-chamber meshes from the cardiac magnetic resonance images of the UK Biobank imaging population. Based on the reconstructed meshes, a 3D+t statistical shape model is learnt to characterise the shape variations and motion patterns of the four cardiac chambers. We reveal the associations of the four-chamber shape model with demographics, anthropometrics, cardiovascular risk factors, and cardiac diseases. Compared to conventional image-derived phenotypes, we validate that the four-chamber shape-derived phenotypes significantly enhance the performance in downstream tasks, including cardiovascular disease classification and heart age prediction. Furthermore, we demonstrate the effectiveness of shape-derived phenotypes in novel applications such as heart shape retrieval and heart re-identification from longitudinal data. To facilitate future research, we will release the learning-based mesh reconstruction pipeline, the four-chamber cardiac shape model, and return all derived four-chamber meshes to the UK Biobank.

Beyond BMI: Smartphone Body Composition Phenotyping for Cardiometabolic Risk Assessment

2026-04-06T23:23:21Z

Body Mass Index (BMI) is a widely accessible but imprecise proxy of cardiometabolic health. While assessing true body composition is superior, gold-standard methods like Dual-Energy X-ray Absorptiometry (DXA) are not scalable. We address this gap by developing and validating "PhotoScan," a method to estimate body composition from smartphone imagery. We pretrained a deep learning model on UK Biobank participants (N=35,323) and fine-tuned on a newly recruited clinical cohort (PhotoBIA cohort, N=677) with diverse ethnicity, age, and body fat distribution, achieving high accuracy against DXA for total body fat percentage (BF%, MAE = 2.15%), Android-to-Gynoid fat ratio (A/G, MAE = 0.11), and visceral-to-subcutaneous fat area ratio (V/S, MAE = 0.09). Generalizability of the model was demonstrated on an independent metabolic health study cohort (MetabolicMosaic cohort, N=132 participants), achieving MAEs of 2.13% for BF%, 0.09 for A/G, and 0.09 for V/S. We then evaluated the clinical utility of these metrics in the MetabolicMosaic cohort by predicting insulin resistance (IR). Adding PhotoScan-derived body composition metrics to baseline demographics model (Age, Sex, BMI) significantly improved insulin resistance classification (Area Under the Receiver Operating Characteristic Curve "AUROC" 76.0% vs 69.2%, DeLong test p=0.002, Net Reclassification Index "NRI" 0.593). Crucially, this accessible smartphone method achieved performance nearly equivalent to adding clinical-grade DXA data to baseline demographics model (AUROC 77.3% vs 69.2%, DeLong test p=0.004, NRI 0.748). These findings demonstrate that smartphone-based phenotyping captures clinically meaningful risk signals missed by BMI and anthropometrics, offering a scalable alternative to DXA for cardiometabolic risk stratification.

Strain-Parameterized Coupled Dynamics and Dual-Camera Visual Servoing for Aerial Continuum Manipulators

2026-03-24T15:33:22Z

Tendon-driven aerial continuum manipulators (TD-ACMs) combine the maneuverability of uncrewed aerial vehicles (UAVs) with the compliance of lightweight continuum robots (CRs). Existing coupled dynamic modeling approaches for TD-ACMs incur high computational costs and do not explicitly account for aerial platform underactuation. To address these limitations, this paper presents a generalized dynamic formulation of a coupled TD-ACM with an underactuated base. The proposed approach integrates a strain-parameterized Cosserat rod model with a rigid-body model of the UAV into a unified Lagrangian ordinary differential equation (ODE) framework on $\mathrm{SE}(3)$, thereby eliminating computationally intensive symbolic derivations. Building upon the developed model, a robust dual-camera image-based visual servoing (IBVS) scheme is introduced. The proposed controller mitigates the field-of-view (FoV) limitations of conventional IBVS, compensates for attitude-induced image motion caused by UAV lateral dynamics, and incorporates a low-level adaptive controller to address modeling uncertainties with formal stability guarantees. Extensive simulations and experimental validation on a compact custom-built prototype demonstrate the effectiveness and robustness of the proposed framework in real-world scenarios.

Cylindrical Metasurface for Efficient Traveling-wave MRI at 7 T

2026-04-20T20:33:14Z

This research focuses on the design and evaluation of an ultrathin cylindrical metasurface for improving the transmit efficiency of traveling-wave magnetic resonance imaging (MRI) of the human brain. To improve efficiency, we matched a travelling waveguide mode to an electrically large, lossy dielectric load using a thin cylindrical metasurface, which occurs to be a task closely related to impedance matching in waveguide circuits in the microwave. This metasurface was designed as a compact and lightweight replacement for a high-permittivity dielectric waveguide previously proposed for the same purpose. The dispersion analysis showed that both structures (waveguide and metasurface) support a similar type of slow-wave propagation, characterized by a uniform magnetic field profile close to the cylinder axis. At the Larmor frequency, the longitudinal wavenumbers showed close agreement. Based on the optimized unit cell geometry of the periodic copper strip grid loaded with PCB capacitors, full numerical model of the cylindrical metasurface in the presence of a voxel human body model was constructed. We also compared the proposed metasurface with the dielectric waveguide in the traveling-wave setup experimentally, including in vivo measurements performed on a healthy volunteer. The proposed metasurface showed improved B1 + homogeneity (by 17.3%), transmit efficiency (by 27.4%), and SAR-efficiency (by 23%) compared to the dielectric waveguide. The proposed cylindrical metasurface, optimized for field enhancement in the human brain at 7 T in the traveling-wave excitation regime, can further improve the transmit efficiency and homogeneity in the region of interest compared to state-of-the-art structures for traveling-wave MRI, at the same time, granting the advantages of light weight and compactness.

Enhancing Hands in 3D Whole-Body Pose Estimation with Conditional Hands Modulator

2026-03-16T02:00:00Z

Accurately recovering hand poses within the body context remains a major challenge in 3D whole-body pose estimation. This difficulty arises from a fundamental supervision gap: whole-body pose estimators are trained on full-body datasets with limited hand diversity, while hand-only estimators, trained on hand-centric datasets, excel at detailed finger articulation but lack global body awareness. To address this, we propose Hand4Whole++, a modular framework that leverages the strengths of both pre-trained whole-body and hand pose estimators. We introduce CHAM (Conditional Hands Modulator), a lightweight module that modulates the whole-body feature stream using hand-specific features extracted from a pre-trained hand pose estimator. This modulation enables the whole-body model to predict wrist orientations that are both accurate and coherent with the upper-body kinematic structure, without retraining the full-body model. In parallel, we directly incorporate finger articulations and hand shapes predicted by the hand pose estimator, aligning them to the full-body mesh via differentiable rigid alignment. This design allows Hand4Whole++ to combine globally consistent body reasoning with fine-grained hand detail. Extensive experiments demonstrate that Hand4Whole++ substantially improves hand accuracy and enhances overall full-body pose quality.

Primitive-cell-resolved Crystallography for Moiré Bilayers from Imaging

2026-03-12T08:39:25Z

Accurate geometric decoding of moiré bilayers from imaging is essential for engineering quantum systems. Existing schemes, limited by identity or aligned assumptions requiring diagonal beating-to-moiré transformations, do not apply to general non-aligned geometries and become underdetermined when buried layers are unresolved. We establish a primitive-cell-resolved moiré crystallography framework that treats the beating-to-moiré relation in full generality and introduces a complete descriptor set $\{θ_r,\boldsymbol{\varepsilon},(T_{Mt},T_{Mb}),N_B\}$, where the integer moiré--layer matrices $(T_{Mt},T_{Mb})$ and the beating number $N_B$ determine the commensurate unit cell. A hybrid analytical--numerical workflow reconstructs buried-layer lattices, solves Diophantine constraints to obtain $(T_{Mt},T_{Mb})$ and $N_B$, and extracts $(θ_r,\varepsilon_b,θ_u,\varepsilon_u)$ with Poisson effects and tensile/compressive branches treated on equal footing. Reanalyzing twisted bilayer graphene, we identify a $N_B=3$ primitive cell rather than a $N_B=9$ aligned supercell, reducing the atomistic basis threefold and correcting the moiré Brillouin-zone construction. The framework provides a crystallographically consistent route from imaging to primitive-cell-resolved atomistic and many-body models.

Synthetic-Child: An AIGC-Based Synthetic Data Pipeline for Privacy-Preserving Child Posture Estimation

2026-03-03T04:50:29Z

Accurate child posture estimation is critical for AI-powered study companion devices, yet collecting large-scale annotated datasets of children is both expensive and ethically prohibitive due to privacy concerns. We present Synthetic-Child, an AIGC-based synthetic data pipeline that produces photorealistic child posture training images with ground-truth-projected keypoint annotations, requiring zero real child photographs. The pipeline comprises four stages: (1) a programmable 3D child body model (SMPL-X) in Blender generates diverse desk-study poses with IK-constrained anatomical plausibility and automatic COCO-format ground-truth export; (2) a custom PoseInjectorNode feeds 3D-derived skeletons into a dual ControlNet (pose + depth) conditioned on FLUX-1 Dev, synthesizing 12,000 photorealistic images across 10 posture categories with low annotation drift; (3) ViTPose-based confidence filtering and targeted augmentation remove generation failures and improve robustness; (4) RTMPose-M (13.6M params) is fine-tuned on the synthetic data and paired with geometric feature engineering and a lightweight MLP for posture classification, then quantized to INT8 for real-time edge deployment. On a real-child test set (n~300), the FP16 model achieves 71.2 AP -- a +12.5 AP improvement over the COCO-pretrained adult-data baseline at identical model capacity. After INT8 quantization the model retains 70.4 AP while running at 22 FPS on a 0.8-TOPS Rockchip RK3568 NPU. In a single-subject controlled comparison with a commercial posture corrector, our system achieves substantially higher recognition rates across most tested categories and responds ~1.8x faster on average. These results demonstrate that carefully designed AIGC pipelines can substantially reduce dependence on real child imagery while achieving deployment-ready accuracy, with potential applications to other privacy-sensitive domains.

Aligning Fetal Anatomy with Kinematic Tree Log-Euclidean PolyRigid Transforms

2026-08-05T05:07:44Z

Automated analysis of articulated bodies is crucial in medical imaging. Existing surface-based models often ignore internal volumetric structures and rely on deformation methods that lack anatomical consistency guarantees. To address this problem, we introduce a differentiable volumetric body model based on the Skinned Multi-Person Linear (SMPL) formulation, driven by a new Kinematic Tree-based Log-Euclidean PolyRigid (KTPolyRigid) transform. KTPolyRigid resolves Lie algebra ambiguities associated with large, non-local articulated motions, and encourages smooth, bijective volumetric mappings. Evaluated on 53 fetal MRI volumes, KTPolyRigid yields deformation fields with significantly fewer folding artifacts. Furthermore, our framework enables robust groupwise image registration and a label-efficient, template-based segmentation of fetal organs. It provides a robust foundation for standardized volumetric analysis of articulated bodies in medical imaging.