https://arxiv.org/api/rnc/xMQWFp1eNDkzt+sMiCNHp34 2026-09-27T19:43:03Z 120 22 0 http://arxiv.org/abs/2608.19055v1 2026-08-19T15:50:29Z

Music-driven character animation enables and enhances transformative applications in entertainment and interactive education. However, synthesizing realistic drumming motion from audio remains challenging due to the inherent tension between high-acceleration dynamics and the need for extreme spatial-temporal precision. Existing approaches, often reliant on motion matching or MIDI input, struggle with generalizing to diverse real-world audio. Moreover, the field lacks standardized evaluation metrics capable of distinguishing precise drumming from noisy motion. In this paper, we introduce a generative diffusion framework featuring a dual-objective loss function that decouples skeletal integrity from drumstick precision, thus enabling centimeter-level stick precision without sacrificing natural body dynamics. Additionally, leveraging our own dataset and data augmentation strategy, the model generalizes to non-curated, in-the-wild audio. To rigorously evaluate performance, we propose two novel metrics: an impact-to-target distance to quantify spatial precision and an audio-motion correlation score to assess temporal alignment. Our quantitative analysis and user studies demonstrate that our system generates high-quality motion that is often indistinguishable from ground-truth performances.

2026-08-19T15:50:29Z Best Paper Award at the 25th ACM SIGGRAPH / Eurographics Symposium on Computer Animation (SCA 2026). For Supplementary Video, see https://studios.disneyresearch.com/2026/08/18/generalized-audio-driven-synthesis-of-precise-drummer-motion/ Álvaro G. Iñesta Mattia Ryffel Amit H. Bermano Robert W. Sumner Martin Guay http://arxiv.org/abs/2608.04722v1 2026-08-05T11:43:21Z

Creating photorealistic 3D human avatars with realistic upper-body motion remains challenging. Existing approaches either focus on the head and overlook hand gestures, or reconstruct the full body but fail to preserve fine-grained facial fidelity and hand pose accuracy. As a result, current methods struggle to capture the subtle dynamics of facial expressions and hand gestures that are crucial for natural human communication. While methods based on full-body parametric models enable avatar reconstruction from monocular or multi-view inputs, they often lack accurate facial animation and detailed hand articulation. To address these limitations, we propose MVFGA, a novel multi-view-consistent pipeline for generating realistic upper-body avatars. Our approach models the face and hands separately and fuses them with a parametric upper-body mesh model, enabling the capture of fine-grained facial expressions and hand poses for accurate upper-body avatar reconstruction. We then splat 3D Gaussians onto the obtained mesh, enabling high-quality rendering of dynamic avatars from novel viewpoints. Furthermore, we introduce MVFGA-MoCap, a multi-view upper-body motion capture dataset featuring controlled facial expression sequences, diverse hand gestures, and free-form communication. Experiments show that MVFGA generates visually realistic avatars with high-fidelity facial expressions and hand motions, outperforming baselines for upper-body avatar animation. Project page: https://dfki-av.github.io/MVFGA/

2026-08-05T11:43:21Z Accepted at SCA 2026 Computer Graphics Forum, 45(8), 2026 Alireza Javanmardi Vippin Kumar Jeetmal Christen Millerdurai Alain Pagani Didier Stricker 10.1111/cgf.70567 http://arxiv.org/abs/2607.19599v1 2026-07-21T22:00:12Z

Existing approaches to frictional contact dynamics typically either modify the Coulomb law to improve numerical robustness or solve the exact law in a fully coupled monolithic form. However, in its reduced form, exact Coulomb friction can be written as a cone complementarity problem with an augmented velocity, which reveals a natural split between a cone-constrained linear response and a scalar non-associated coupling induced by tangential velocity. We exploit this structure in the solver design. Our method uses an outer iteration to update the non-associated coupling explicitly, and an inner solve for a strongly convex cone-constrained quadratic program. This separation also makes the inner solver modular, so different numerical schemes can be used without changing the outer iteration. We evaluate the method on rigid-body benchmarks with stick-slip transitions and frictional stacking, and show that it reproduces exact Coulomb complementarity without smoothing or relaxing the friction law.

2026-07-21T22:00:12Z 14 pages. Accepted to SCA 2026 (ACM SIGGRAPH / Eurographics Symposium on Computer Animation); published open access in Computer Graphics Forum. DOI: 10.1111/cgf.70576. Project page: https://www.cs.ubc.ca/research/fbf-friction Computer Graphics Forum 45(8), 2026 Hongcheng Song Ye Fan Uri M. Ascher Dinesh K. Pai 10.1111/cgf.70576 http://arxiv.org/abs/2607.10408v1 2026-07-11T17:19:32Z

Creating realistic 3D human-human interactions in virtual environments is challenging due to the high degrees of freedom in the human body and the need for physically accurate poses that do not collide with each other. Traditional methods for human-human interaction are based on motion tracking or 3D body reconstruction, but lack generative capabilities. Recent generative methods enable the synthesis of individual or interacting motions via text or image input, but generally fall short in modeling close interactions. This paper introduces a novel generative model for close 3D human-human interactions using a conditional variational autoencoder (cVAE), which generates poses for one human conditioned on the pose of another, allowing for controlled and diverse interaction synthesis. To train our model, we address two underlying long-standing challenges in the field of human-human interaction: data scarcity, for which we propose an automated supervised data augmentation strategy that generates synthetic yet realistic interaction poses; and collision awareness in generative approaches, for which we propose a self-supervised loss based on a collision resolution technique using volumetric proxies to ensure physically correct interactions. We extensively evaluate the capabilities of our model, and demonstrate a wide variety of plausible and physically correct interactions, not possible to generate with current state-of-the-art methods.

2026-07-11T17:19:32Z Presented at SCA 2026 Gonzalo Gómez-Nogales Marc Comino-Trinidad Andrés Casado-Elvira Dan Casas 10.1111/cgf.70561 http://arxiv.org/abs/2607.04796v1 2026-07-06T08:30:24Z

Recent research in differentiable light transport extends the utility of computer graphics algorithms beyond traditional image generation, offering powerful tools for physical inverse design. In architectural and automotive applications, visual discomfort from glare is a critical design rating, traditionally quantified by the discrete CIE Unified Glare Rating (UGR). The standard UGR formulation relies on strict binary thresholds, making it fundamentally incompatible with smooth gradient-based inverse rendering. In this paper, we introduce a continuous, fully differentiable proxy for UGR. To resolve the severe optimisation instabilities caused by Monte Carlo variance at low sample densities, we introduce a differentiable optical scattering pass that simulates the Point Spread Function (PSF) of the human eye to heal fractured evaluation masks. We replace the discrete UGR step function with a tunable sigmoid boundary, enabling gradients to flow smoothly from the psychophysical measure back to the physical scene parameters. We deploy this differentiable framework to systematically reduce glare across three radiometric domains: surface-side microgeometry roughening, boundary-side index of refraction (IOR) optimisation, and source-side emitter gobo masking. By transforming a passive perceptual evaluation into an active loss landscape, our framework provides a robust, physics-based pipeline for optimizing visual comfort in complex global illumination environments.

2026-07-06T08:30:24Z 15 pages, 16 figures. Published in Proceedings of the Eurographics Symposium on Rendering (EGSR) 2026, Symposium Track. This is the authors' version; the definitive version is available at the Eurographics Digital Library Eurographics Symposium on Rendering 2026 (Symposium Track) Linas Beresna Eugene Fiume 10.2312/sr.20261013 http://arxiv.org/abs/2607.04341v1 2026-07-05T14:51:43Z

This state-of-the-art report provides an overview of controllable 3D human avatar creation. We describe current 3D avatar systems, which typically consist of three stages: (i) learning priors of human appearance and motion, (ii) creating a personalized avatar, and (iii) animating the avatar. To limit the scope, we focus on the prior learning and avatar creation stages. We define current avatar representations and introduce a taxonomy that categorizes existing work along multiple axes, including body regions and employed priors. We review methods for full-body and head avatars, as well as layered representations that decompose the body into components such as hands, hair, and garments. Finally, we outline common underlying principles, reference key literature for newcomers, and discuss open challenges and future research directions.

2026-07-05T14:51:43Z Eurographics 2026 State-of-the-Art Report (STAR). Project page: https://wojciechzielonka.com/how-to-build-digital-humans/ Wojciech Zielonka Tobias Kirschstein Timo Bolkart Simon Giebenhain Vanessa Sklyarova Xiang Deng Donglai Xiang Shunsuke Saito Yebin Liu Matthias Niessner Justus Thies http://arxiv.org/abs/2606.30869v1 2026-06-29T20:01:25Z

3D Gaussian Splatting (3DGS) is a popular representation for radiance field reconstruction, distinguished by the rendering speed of its rasterization-based renderer. While 3D Gaussians can also be ray traced, this approach has so far been slower, with 3D Gaussian Ray Tracing (3DGRT) taking nearly one order of magnitude longer to optimize. To address this, we present GRay, a fast ray tracer for 3D Gaussians designed to close this performance gap and match 3DGS's speed. Our method leverages the algorithmic difference between both approaches: unlike rasterization, ray tracing evaluates only Gaussians that are actually intersected by a ray, leading to potentially logarithmic--rather than linear--scaling in the number of primitives. This property allows ray tracing to better exploit dense scenes composed of numerous tiny Gaussians, a configuration which has largely been overlooked. Notably, we show that dense initialization--which creates many small Gaussians--slows down rasterization, but instead speeds up ray tracing. Designed to leverage this effect, GRay renders nearly 4x faster and optimizes nearly 10x faster than 3DGRT while maintaining similar quality, and has competitive speed with 3DGS albeit at somewhat lower quality. Code is available at https://repo-sam.inria.fr/nerphys/gray.

2026-06-29T20:01:25Z 12 pages plus supplementary material, 33 pages total; Proceedings of the ACM on Computer Graphics and Interactive Techniques, I3D 2026 Proc. ACM Comput. Graph. Interact. Tech. 9, 1, Article 14, 19 pages, 2026 Yohan Poirier-Ginter Jean-François Lalonde George Drettakis 10.1145/3804496 http://arxiv.org/abs/2606.16457v1 2026-06-15T09:30:03Z

Conditional diffusion image generators can be repurposed for editing through inversion, without the need for large-scale paired fine-tuning data. However, producing high-quality, targeted edits while maintaining image identity and global consistency remains challenging, as weakly conditioned inversion often embeds conflicting image features into the noise. We demonstrate that incorporating a residual image encoding as additional conditioning enables both improved identity preservation and better editability. We optimize this residual encoding to provide a strong conditioning signal for reconstruction, thereby reducing the reliance on inversion and susceptibility to its aforementioned pitfalls. To ensure this residual does not interfere with desired edits, we incorporate a gradient reversal-based optimization strategy that disentangles the residual from the edited condition. We illustrate our method's ability to produce high-fidelity results across precise intrinsic-based editing and relighting, and show proof-of-concept text-guided manipulation.

2026-06-15T09:30:03Z Accepted to the EGSR 2026 journal track Computer Graphics Forum 45(4), e70551 (2026) Ahmet Canberk Baykal Valentin Deschaintre Yannick Hold-Geoffroy Michael Fischer Anna Frühstück Cengiz Öztireli Iliyan Georgiev 10.1111/cgf.70551 http://arxiv.org/abs/2605.00219v1 2026-04-30T20:48:14Z

We present VkSplat, a high-performance, cross-vendor 3D Gaussian Splatting (3DGS) training pipeline implemented fully in Vulkan compute, addressing performance and compatibility limitation of existing training pipelines. With various optimizations, we achieve $3.3\times$ speed and $33\%$ VRAM reduction over CUDA+PyTorch baseline, maintaining quality, and demonstrating compatibility across GPU vendors. To the best of our knowledge, this is the first fully-Vulkan-based 3DGS training pipeline that achieves state-of-the-art performance. Code: \href{https://github.com/harry7557558/vksplat}{https://github.com/harry7557558/vksplat}

2026-04-30T20:48:14Z Submitted to Eurographics 2026 - Short Papers Jingxiang Chen Mohamed Ibrahim Yang Liu 10.2312/egs.20261024 http://arxiv.org/abs/2604.19127v1 2026-04-21T06:19:22Z

UV-parameterized Gaussian Splatting (UVGS) maps an unstructured set of 3D Gaussians to a regular UV tensor, enabling compact storage and explicit control of representation capacity. Existing UVGS, however, uses a deterministic spherical pro- jection to assign Gaussians to UV locations. Because this mapping ignores the global Gaussian distribution, it often leaves many UV slots empty while causing frequent collisions in dense regions. We reinterpret UV mapping as a capacity-allocation problem under a fixed UV budget and propose OT-UVGS, a lightweight, separable one-dimensional optimal-transport-inspired mapping that globally couples assignments while preserving the original UVGS representation. The method is implemented with rank-based sorting, has O(N log N) complexity for N Gaussians, and can be used as a drop-in replacement for spherical UVGS. Across 184 object-centric scenes and the Mip-NeRF dataset, OT-UVGS consistently improves peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and Learned Perceptual Image Patch Similarity (LPIPS) under the same UV resolution and per-slot capacity (K=1). These gains are accompanied by substantially better UV utilization, including higher non-empty slot ratios, fewer collisions, and higher Gaussian retention. Our results show that revisiting the mapping alone can unlock a significant fraction of the latent capacity of UVGS.

2026-04-21T06:19:22Z Accepted to Eurographics 2026 Short Papers Eurographics 2026 - Short Papers, The Eurographics Association, 2026, 4 pages Byunghyun Kim 10.2312/egs.20261023 http://arxiv.org/abs/2604.09260v1 2026-04-10T12:20:07Z

Standard object detectors typically treat architectural elements independently, often resulting in facade parsings that lack the structural coherence required for downstream procedural reconstruction. We address this limitation by augmenting the YOLOv8 training objective with a custom lightweight alignment loss. This regularization encourages grid-consistent arrangements of bounding boxes during training, effectively injecting geometric priors without altering the standard inference pipeline. Experiments on the CMP dataset demonstrate that our method successfully improves structural regularity, correcting alignment errors caused by perspective and occlusion while maintaining a controllable trade-off with standard detection accuracy.

2026-04-10T12:20:07Z 4 pages, 4 figures, EUROGRAPHICS 2026 Short Paper Maciej Janicki Aleksander Plocharski Przemyslaw Musialski http://arxiv.org/abs/2604.08411v1 2026-04-09T16:11:01Z

Current data-driven floor plan generation methods often reproduce the ergonomic inefficiencies found in real-world training datasets. To address this, we propose a novel approach that integrates architectural design principles directly into a transformer-based generative process. We formulate differentiable loss functions based on established architectural standards from literature to optimize room adjacency and proximity. By guiding the model with these ergonomic priors during training, our method produces layouts with significantly improved livability metrics. Comparative evaluations show that our approach outperforms baselines in ergonomic compliance while maintaining high structural validity.

2026-04-09T16:11:01Z 4 pages, 2 figures, EUROGRAPHICS 2026 Short Paper Piotr Nieciecki Aleksander Plocharski Przemyslaw Musialski http://arxiv.org/abs/2604.01274v1 2026-04-01T18:00:03Z

Estimating correspondences between deformed shape instances is a long-standing problem in computer graphics; numerous applications, from texture transfer to statistical modelling, rely on recovering an accurate correspondence map. Many methods have thus been proposed to tackle this challenging problem from varying perspectives, depending on the downstream application. This state-of-the-art report is geared towards researchers, practitioners, and students seeking to understand recent trends and advances in the field. We categorise developments into three paradigms: spectral methods based on functional maps, combinatorial formulations that impose discrete constraints, and deformation-based methods that directly recover a global alignment. Each school of thought offers different advantages and disadvantages, which we discuss throughout the report. Meanwhile, we highlight the latest developments in each area and suggest new potential research directions. Finally, we provide an overview of emerging challenges and opportunities in this growing field, including the recent use of vision foundation models for zero-shot correspondence and the particularly challenging task of matching partial shapes.

2026-04-01T18:00:03Z 35 pages and 15 figures; Eurographics 2026 STAR; Project page: https://nonrigid-shape-correspondences.github.io Aleksei Zhuravlev Lennart Bastian Dongliang Cao Nafie El Amrani Paul Roetzer Viktoria Ehm Riccardo Marin Hiroki Nishizawa Shigeo Morishima Christian Theobalt Nassir Navab Daniel Cremers Florian Bernard Zorah Lähner Vladislav Golyanik http://arxiv.org/abs/2602.18319v1 2026-02-20T16:19:19Z

We present the first motion generation system for playtesting virtual reality (VR) games. Our player model generates VR headset and handheld controller movements from in-game object arrangements, guided by style exemplars and aligned to maximize simulated gameplay score. We train on the large BOXRR-23 dataset and apply our framework on the popular VR game Beat Saber. The resulting model Robo-Saber produces skilled gameplay and captures diverse player behaviors, mirroring the skill levels and movement patterns specified by input style exemplars. Robo-Saber demonstrates promise in synthesizing rich gameplay data for predictive applications and enabling a physics-based whole-body VR playtesting agent.

2026-02-20T16:19:19Z 13 pages, 15 figures. Accepted to Eurographics 2026. Project page: https://robo-saber.github.io/ Nam Hee Kim Jingjing May Liu Jaakko Lehtinen Perttu Hämäläinen James F. O'Brien Xue Bin Peng http://arxiv.org/abs/2602.12949v1 2026-02-13T14:15:46Z

Rendering diffuse global illumination in real-time is often approximated by pre-computing and storing irradiance in a 3D grid of probes. As long as most of the scene remains static, probes approximate irradiance for all surfaces immersed in the irradiance volume, including novel dynamic objects. This approach, however, suffers from aliasing artifacts and high memory consumption. We propose Neural Irradiance Volume (NIV), a neural-based technique that allows accurate real-time rendering of diffuse global illumination via a compact pre-computed model, overcoming the limitations of traditional probe-based methods, such as the expensive memory footprint, aliasing artifacts, and scene-specific heuristics. The key insight is that neural compression creates an adaptive and amortized representation of irradiance, circumventing the cubic scaling of grid-based methods. Our superior memory-scaling improves quality by at least 10x at the same memory budget, and enables a straightforward representation of higher-dimensional irradiance fields, allowing rendering of time-varying or dynamic effects without requiring additional computation at runtime. Unlike other neural rendering techniques, our method works within strict real-time constraints, providing fast inference (around 1 ms per frame on consumer GPUs at full HD resolution), reduced memory usage (1-5 MB for medium-sized scenes), and only requires a G-buffer as input, without expensive ray tracing or denoising.

2026-02-13T14:15:46Z Accepted at Eurographics 2026 Arno Coomans Giacomo Nazzaro Edoardo A. Dominici Christian Döring Floor Verhoeven Konstantinos Vardis Markus Steinberger http://arxiv.org/abs/2512.09162v3 2026-03-19T12:23:13Z

Recent advancements in Gaussian Splatting have enabled increasingly accurate reconstruction of photorealistic head avatars, opening the door to numerous applications in visual effects, videoconferencing, and virtual reality. This, however, comes with the lack of intuitive editability offered by traditional triangle mesh-based methods. In contrast, we propose a method that combines the accuracy and fidelity of 2D Gaussian Splatting with the intuitiveness of UV texture mapping. By embedding each canonical Gaussian primitive's local frame into a patch in the UV space of a template mesh in a computationally efficient manner, we reconstruct continuous editable material head textures from a single monocular video on a conventional UV domain. Furthermore, we leverage an efficient physically based reflectance model to enable relighting and editing of these intrinsic material maps. Through extensive comparisons with state-of-the-art methods, we demonstrate the accuracy of our reconstructions, the quality of our relighting results, and the ability to provide intuitive controls for modifying an avatar's appearance and geometry via texture mapping without additional optimization.

2025-12-09T22:19:28Z Accepted to Eurographics 2026. Project page: https://kelianb.github.io/GTAvatar/ Kelian Baert Mae Younes Francois Bourel Marc Christie Adnane Boukhayma 10.1111/cgf.70351 http://arxiv.org/abs/2511.09397v2 2025-12-15T18:12:41Z

Recent advances in 3D Gaussian Splatting (3DGS) have achieved state-of-the-art results for novel view synthesis. However, efficiently capturing high-fidelity reconstructions of specific objects within complex scenes remains a significant challenge. A key limitation of existing active reconstruction methods is their reliance on scene-level uncertainty metrics, which are often biased by irrelevant background clutter and lead to inefficient view selection for object-centric tasks. We present OUGS, a novel framework that addresses this challenge with a more principled, physically-grounded uncertainty formulation for 3DGS. Our core innovation is to derive uncertainty directly from the explicit physical parameters of the 3D Gaussian primitives (e.g., position, scale, rotation). By propagating the covariance of these parameters through the rendering Jacobian, we establish a highly interpretable uncertainty model. This foundation allows us to then seamlessly integrate semantic segmentation masks to produce a targeted, object-aware uncertainty score that effectively disentangles the object from its environment. This allows for a more effective active view selection strategy that prioritizes views critical to improving object fidelity. Experimental evaluations on public datasets demonstrate that our approach significantly improves the efficiency of the 3DGS reconstruction process and achieves higher quality for targeted objects compared to existing state-of-the-art methods, while also serving as a robust uncertainty estimator for the global scene.

2025-11-12T15:08:46Z Conditionally accepted to Eurographics 2026 (five reviewers) Haiyi Li Qi Chen Denis Kalkofen Hsiang-Ting Chen http://arxiv.org/abs/2510.22712v2 2026-03-09T10:16:26Z

Human motion is fundamentally driven by continuous physical interaction with the environment. Whether walking, running, or simply standing, the forces exchanged between our feet and the ground provide crucial insights for understanding and reconstructing human movement. Recent advances in wearable insole devices offer a compelling solution for capturing these forces in diverse, real-world scenarios. Sensor insoles pose no constraint on the users' motion (unlike mocap suits) and are unaffected by line-of-sight limitations (in contrast to optical systems). These qualities make sensor insoles an ideal choice for robust, unconstrained motion capture, particularly in outdoor environments. Surprisingly, leveraging these devices with recent motion reconstruction methods remains largely unexplored. Aiming to fill this gap, we present Step2Motion, the first approach to reconstruct human locomotion from multi-modal insole sensors. Our method utilizes pressure and inertial data-accelerations and angular rates-captured by the insoles to reconstruct human motion. We evaluate the effectiveness of our approach across a range of experiments to show its versatility for diverse locomotion styles, from simple ones like walking or jogging up to moving sideways, on tiptoes, slightly crouching, or dancing.

2025-10-26T15:12:02Z Eurographics 2026 Jose Luis Ponton Eduardo Alvarado Lin Geng Foo Nuria Pelechano Carlos Andujar Marc Habermann 10.1111/cgf.70405 http://arxiv.org/abs/2509.23607v2 2026-02-17T05:27:01Z

In the field of 3D content generation, single image scene reconstruction methods still struggle to simultaneously ensure the quality of individual assets and the coherence of the overall scene in complex environments, while texture editing techniques often fail to maintain both local continuity and multi-view consistency. In this paper, we propose a novel system ZeroScene, which leverages the prior knowledge of large vision models to accomplish both single image-to-3D scene reconstruction and texture editing in a zero-shot manner. ZeroScene extracts object-level 2D segmentation and depth information from input images to infer spatial relationships within the scene. It then jointly optimizes 3D and 2D projection losses of the point cloud to update object poses for precise scene alignment, ultimately constructing a coherent and complete 3D scene that encompasses both foreground and background. Moreover, ZeroScene supports texture editing of objects in the scene. By imposing constraints on the diffusion model and introducing a mask-guided progressive image generation strategy, we effectively maintain texture consistency across multiple viewpoints and further enhance the realism of rendered results through Physically Based Rendering (PBR) material estimation. Experimental results demonstrate that our framework not only ensures the geometric and appearance accuracy of generated assets, but also faithfully reconstructs scene layouts and produces highly detailed textures that closely align with text prompts.

2025-09-28T03:21:12Z 16 pages, 15 figures, Eurographics 2026, Project page: https://xdlbw.github.io/ZeroScene/ Xiang Tang Ruotong Li Xiaopeng Fan http://arxiv.org/abs/2509.22276v2 2026-03-07T17:18:02Z

We propose a material-aware optimization framework for high-fidelity mesh reconstruction from multi-view images based on 3D Gaussian Splatting, referred to as GS-2M. Previous works handle these tasks separately and struggle to reconstruct highly reflective surfaces, often relying on priors from external models to enhance the decomposition results. Conversely, our method addresses these two problems by jointly optimizing attributes relevant to the quality of rendered depth and normals, maintaining geometric details while being resilient to reflective surfaces. Although contemporary works effectively solve these tasks together, they often employ sophisticated neural components to learn scene properties, which hinders their performance at scale. To further eliminate these neural components, we propose a novel roughness supervision strategy based on multi-view photometric variation. When combined with a carefully designed loss and optimization process, our unified framework produces reconstruction results comparable to state-of-the-art methods, delivering accurate triangle meshes even for reflective surfaces. We validate the effectiveness of our approach with widely used datasets from previous works and qualitative comparisons with state-of-the-art surface reconstruction methods. Project page: https://ndming.github.io/publications/gs2m/.

2025-09-26T12:43:33Z This is the author's version of a paper accepted to Eurographics 2026, to appear in Computer Graphics Form. The final version will be available via Wiley Dinh Minh Nguyen Malte Avenhaus Thomas Lindemeier 10.1111/cgf.70347 http://arxiv.org/abs/2506.11483v4 2026-05-27T17:57:47Z

We introduce Capsule, a mechanism for seamlessly sharing datacenter resources across multiple players. It decouples player-local and global states to achieve isolation and to maximize cross-player sharing. Our evaluations show that Capsule increases datacenter resource utilization by accommodating up to 2.25x more players without degrading the user experience. This improvement stems from Capsule consuming up to 1.43x less GPU, 3.11x less VRAM, 3.7x less CPU, and 3.87x less RAM compared to the baseline. We evaluated Capsule across four applications and various hardware configurations, including three distinct servers and a multi-server cluster. These results demonstrate that the Capsule design is portable to other game engines.

2025-06-13T06:12:31Z 4 main pages, 6 more appendix pages, 8 figures; an extended version of EUROGRAPHICS 2026 short paper Zhouheng Du Nima Davari Li Li Wei Sen Loi Nodir Kodirov 10.2312/egs.20261014 http://arxiv.org/abs/2505.17778v2 2026-03-12T12:42:46Z

Diffusion-based scene text synthesis has progressed rapidly, yet existing methods commonly rely on additional visual conditioning modules and require large-scale annotated data to support multilingual generation. In this work, we revisit the necessity of complex auxiliary modules and further explore an approach that simultaneously ensures glyph accuracy and achieves high-fidelity scene integration, by leveraging diffusion models' inherent capabilities for contextual reasoning. To this end, we introduce TextFlux, a DiT-based framework that enables multilingual scene text synthesis. The advantages of TextFlux can be summarized as follows: (1) OCR-free model architecture. TextFlux eliminates the need for OCR encoders (additional visual conditioning modules) that are specifically used to extract visual text-related features. (2) Strong multilingual scalability. TextFlux is effective in low-resource multilingual settings, and achieves strong performance in newly added languages with fewer than 1,000 samples. (3) Streamlined training setup. TextFlux is trained with only 1% of the training data required by competing methods. (4) Controllable multi-line text generation. TextFlux offers flexible multi-line synthesis with precise line-level control, outperforming methods restricted to single-line or rigid layouts. Extensive experiments and visualizations demonstrate that TextFlux outperforms previous methods in both qualitative and quantitative evaluations.

2025-05-23T11:46:46Z Accepted to Eurographics 2026 (Computer Graphics Forum) Yu Xie Jielei Zhang Pengyu Chen Weihang Wang Longwen Gao Peiyi Li Qian Qiao Zhouhui Lian