https://arxiv.org/api/Zi8owlvCqrZNQqiXELY+E+370rU 2026-09-16T17:44:58Z 20 70 0 http://arxiv.org/abs/2609.16465v1 2026-09-15T00:35:17Z

We present an automated pipeline that converts hair-card models into high-quality strand-based hairstyles. Given a collection of textured triangular or quad strips as input, our method produces a strand-based representation that preserves the original hairstyle while enriching it with fine-scale geometric detail and adhering to standard production requirements: strands originate from the scalp, roots are uniformly distributed, and the hair volume is plausibly filled. The resulting assets are directly compatible with strand-based rendering, physics-based simulation, and common grooming modifiers (e.g., clumping, curling, noise) for enhanced realism and artistic control. We validate our approach on a large and diverse set of hairstyles, including short and long hair, curly styles, and complex styles such as buns and ponytails.

2026-09-15T00:35:17Z 22 pages, 30 figures, 5 tables. Dataset: https://huggingface.co/datasets/HairCS2027/HairCS Zixuan Lu University of Utah Tongtong Wang LIGHTSPEED Yuefan Shen LIGHTSPEED Zhongtian Zheng LIGHTSPEED Chenfanfu Jiang UCLA Yin Yang University of Utah Kui Wu LIGHTSPEED http://arxiv.org/abs/2608.13679v1 2026-08-13T18:22:08Z

Creating high-quality strand-based hairstyles in current production pipelines remains heavily dependent on skilled artists and time-consuming manual authoring, making it costly and difficult to scale. Existing learning-based methods have advanced image-driven hair reconstruction, but typically require large, diverse training datasets, struggle to generalize to complex styles such as buns and ponytails, and often operate in representations that are not directly compatible with strand-based modeling, editing, and simulation. We present a novel automatic pipeline that combines the capabilities of Large Reconstruction Models (LRMs), Large Multimodal Models (LMMs), and classical geometry processing to generate high-quality strand-based hairstyles from single-view images. Our approach produces detailed, production-ready strand geometry without task-specific training or data collection and can handle a wide variety of hairstyles, including straight and curly hair, short and long styles, and challenging structured configurations such as ponytails and buns. Across this diverse set of examples, our method generates visually compelling strand-level reconstructions within only a few minutes, making it well-suited for integration into modern digital human workflows.

2026-08-13T18:22:08Z Conghui Hao Tao Huang Yuefan Shen Tongtong Wang Zhongtian Zheng Kui Wu http://arxiv.org/abs/2607.23861v1 2026-07-26T22:08:13Z

We present DynHair, a novel method for tracking and modeling dynamic hair for human head avatars. From video input, we reconstruct a dynamic head avatar with an explicit strand-based hair representation using structured 3D Gaussian Splatting. In contrast to the face region of human head avatars, which can be modeled with 3D Gaussians that are attached or generated with respect to some expressive 3D head model, hair is particularly challenging as it exhibits dynamic motion effects. Therefore, we present a novel method that models the dynamic deformations of the hair strands using a temporal network that is conditioned on angular velocity and acceleration of the head, as well as relative gravity. Specifically, an LSTM encodes the motion history and modulates per-point strand features via FiLM conditioning which further used by MLP to produce physically plausible displacements to canonical hairstyle. We jointly optimize this motion and appearance representation of the hair, with a 3DGS-based representation of the face-region, via differentiable Gaussian splatting with photometric, geometric, and physics-based supervision. As a result of our method, we retrieve hair tracking of the training video data and an animatable head avatar with controllable hair dynamics. In our experiments, we demonstrate state-of-the-art performance in terms of hair dynamics, temporal consistency, and generalization across subjects.

2026-07-26T22:08:13Z Project page: https://dynhair.is.tue.mpg.de/ Vanessa Sklyarova Haonan Chen Berna Kabadayi Tobias Kirschstein Zicong Fan Xi Wang Gerard Pons-Moll Matthias Nießner Marc Pollefeys Michael J. Black Justus Thies http://arxiv.org/abs/2607.22103v1 2026-07-24T08:55:39Z

Realistic simulation of curly hair is challenging due to the tight coupling between macroscopic strand deformation and high-frequency geometric details such as waves and helices. In this paper, we propose a curly hair model that decomposes each strand into curly elements, consisting of a rod-base configuration and an analytically defined high-frequency wrinkles represented by planar waves or volumetric helices, with deformation governed primarily by bending for wavy hair and twisting for spiral hair. A curvature-energy splitting scheme separates stretching, buckling, and bending contributions, and efficient energy approximations improve numerical robustness and reduce computational cost without degrading visual fidelity. We further introduce a hybrid collision handling strategy that combines coarse collision proxies for the base configuration with analytical treatment of high-frequency details, and adapt guide-strand interpolation to our curly finite-element representation to generate dense hair while preserving fine structure. Experiments demonstrate stable, efficient, and visually faithful simulation of curly hair across diverse scenarios.

2026-07-24T08:55:39Z Xinming Pei Zhendong Wang Lei Lan Weiwei Xu Yin Yang Huamin Wang http://arxiv.org/abs/2607.09811v1 2026-07-10T02:41:14Z

We present a framework for understanding and generating feature rich hair strands. Drawing upon both scientific and cultural expertise, we define strand texture as the various distinctive patterns (curling, switchbacks, twist, etc.) that are formed by forces internal to a hair strand. We begin by proposing a novel five-dimensional parameter space, intended to be a bijection with naturally occurring hair strand textures. This encoding is both qualitatively accessible, allowing users to readily locate their own hair in the parameter space, and quantitatively precise, allowing the generation of individual strands from texture inputs. Importantly, strand texture should be independent from the overall strand direction. In order to disentangle strand texture from the overall strand direction, we identify centerline geometry and use it to map strands into a canonical space (a strand texture space). We construct centerlines using a novel method that cleanly distills complex hair grooms, separating the strand texture from the overall style (parameterized by style guides). We enable the creation of new strands conforming to our parametric description of texture via a generative artificial intelligence approach supervised by a separate neural network trained to label candidate strands according to our five-parameter description. The ability to create new strands conforming to any desired texture enables groom editing using either texture transfer or user-provided inputs. We demonstrate results on a variety of hair types.

2026-07-10T02:41:14Z 18 pages, 18 figures Sarah Jobalia Yitong Deng Carolyn Smith Ronald Fedkiw http://arxiv.org/abs/2607.04230v1 2026-07-05T11:05:45Z

In this work we propose an efficient deferred software rasterization pipeline for real-time rendering of strand-based hair using hair meshes. Hair plays a crucial role in creating expressive 3D characters, yet strand-based approaches are often restricted to high-end hardware and typically applied to only a small number of hero characters. Hair meshes have proven to be an efficient representation capable of handling a wide variety of groom styles, but existing mesh shader-based implementations still suffer from significant bottlenecks. In this work, we address these limitations with a software rasterization approach that improves performance and compatibility. Our method enables efficient far-field strand-based hair rendering-even at a single sample per pixel-by combining deferred shading with a strand filtering and reconstruction step, while requiring only minimal hardware support. To further enhance scalability, we introduce a level-of-detail (LOD) scheme that adapts hair representation and shading complexity based on viewing distance and screen-space coverage, reducing computational cost further while preserving visual fidelity. To the best of our knowledge, this is the first approach to achieve this combination of efficiency, flexibility, scalability, and broad hardware compatibility.

2026-07-05T11:05:45Z 19 pages Proc. ACM Comput. Graph. Interact. Tech. 9, 4, Article 58 (July 2026) Lukas Lipp Adrian Jarabo Michael Wimmer Lukas Bode 10.1145/3820015 http://arxiv.org/abs/2606.15238v1 2026-06-13T10:34:10Z

The fundamental limitation of traditional strand-based modeling is not simply data scarcity, but the ill-posedness of inferring complex 3D fields from 2D imagery without structural constraints. This unconstrained regression leads to catastrophic failures in resolving both global occlusion (e.g., in ponytails) and local directionality (e.g., in curls), resulting in over-smoothed, plausible-but-incorrect geometries. To resolve this, we integrate the strong geometric priors of Large Reconstruction Models (LRMs) into the strand generation pipeline. Using the LRM mesh as a structural anchor, we employ a novel Dual Orientation AutoEncoder to lift coarse geometry into high-fidelity strands. By resolving vector field singularities through latent-space optimization and surface-guided refinement, our method effectively disentangles complex topological structures, setting a new benchmark for robustness and accuracy in hair reconstruction.

2026-06-13T10:34:10Z ACM SIGGRAPH 2026 Conference Paper Yuefan Shen Yican Dong Xiufeng Huang Zhongtian Zheng Youyi Zheng Kui Wu http://arxiv.org/abs/2606.08041v1 2026-06-06T08:04:07Z

Facial hair is a defining trait of personal identity, yet remains a critical bottleneck for digital avatars. Recent volumetric methods achieve photorealism but bake hair into the underlying face geometry, preventing editability and failing to resolve sparse, strand-like structures. Meanwhile, scalp-hair reconstruction methods target dense hair volumes and do not transfer to the sparse, spatially-varying nature of facial hair. We present a pipeline that automatically reconstructs facial hair -- beard, mustache, lashes, and brows -- from multi-view images, converting an unstructured 3D Gaussian representation into an explicit curve-based strand representation. We resolve geometric ambiguities in four stages: (i) optimizing 3D Gaussians constrained by tracked head geometry to enforce early ray termination and suppress sub-surface noise; (ii) tracing continuous strands robust to frequent crossings and extreme curvature; (iii) grounding strands to the surface and resolving root-tip ambiguity via a physically-motivated prior; and (iv) refining the reconstruction through opacity-driven density control under photometric optimization. To our knowledge, this is the first method to reconstruct high-fidelity facial hair strands from a 3D Gaussian representation. The recovered strands faithfully preserve the orientation and sparsity patterns characteristic of facial hair, and yield assets immediately suitable for downstream production tasks, including facial animation and physical simulation, geometric grooming and transfer, appearance editing, and physics-based rendering.

2026-06-06T08:04:07Z 27 pages, 16 figures, supplementary included Jaeseong Lee Giljoo Nam Adrian Jarabo Carlos Aliaga http://arxiv.org/abs/2605.17557v3 2026-08-31T17:25:49Z

We propose a lightweight real-time method for reconstructing strand-based hair G-Buffers from severely undersampled rasterized inputs. Our pipeline first applies neural spatial reconstruction and temporal accumulation to recover hair coverage, i.e., fractional hair visibility within a pixel, and tangent. It then uses a tangent-guided reconstruction step to complete the position, which is subsequently used for physically based deferred hair shading. We evaluate our method across a diverse set of hairstyles, including straight, wavy, afro, and ponytail styles, under both static and dynamic scenarios. Our method achieves higher hair reconstruction quality than general industrial neural reconstruction solutions such as DLSS and FSR.

2026-05-17T17:37:57Z ACM SIGGRAPH ASIA 2026 Conference Paper Chenghao Wu Yuefan Shen Tao Huang Kai Yan Zahra Montazeri Kui Wu http://arxiv.org/abs/2605.08824v1 2026-05-09T09:19:36Z

Hair is a rich medium of visual and cultural expression, yet its digital modeling remains challenging due to the duality of fluidity and structure. Many existing generative approaches rely primarily on continuous diffusion fields, which entangle global topology with local texture and obscure the semantic and structural organization of hairstyles. To address this, we propose HairGPT, a strand-centric framework that treats strands as generative primitives and formulates realistic 3D hairstyle synthesis as a dual-decoupled autoregressive sequence modeling problem. Our method applies spatial decoupling across semantic scalp regions and structural decoupling along a hierarchical strand representation, progressing from global layout to fine-grained style. We further introduce a geometric tokenizer and region-aware semantic annotations to guide strand-level generation, enabling compositional editing, synthesis of rare and complex hairstyles, and adaptation to stylized domains. By aligning generative modeling with the workflow of digital grooming, HairGPT turns hair generation from opaque texture synthesis into a structured and semantically controllable authoring process, supporting robust semantic conditioning and high-fidelity results across realistic and stylized domains. Project Page: https://haiminluo.github.io/hairgpt/

2026-05-09T09:19:36Z Accepted to SIGGRAPH 2026 (Journal Track) Haimin Luo Min Ouyang Lan Xu Jingyi Yu 10.1145/3811350 http://arxiv.org/abs/2604.06467v1 2026-04-07T21:09:52Z

Realistic digital avatars require expressive and dynamic hair motion; however, most existing head avatar methods assume rigid hair movement. These methods often fail to disentangle hair from the head, representing it as a simple outer shell and failing to capture its natural volumetric behavior. In this paper, we address these limitations by introducing PhysHead, a hybrid representation for animatable head avatars with realistic hair dynamics learned from multi-view video. At the core is a 3D Gaussian-based layered representation of the head. Our approach combines a 3D parametric mesh for the head with strand-based hair, which can be directly simulated using physics engines. For the appearance model, we employ Gaussian primitives attached to both the head mesh and hair segments. This representation enables the creation of photorealistic head avatars with dynamic hair behavior, such as wind-blown motion, overcoming the constraints of rigid hair in existing methods. However, these animation capabilities also require new training schemes. In particular, we propose the use of VLM-based models to generate appearance of regions that are occluded in the dynamic training sequences. In quantitative and qualitative studies, we demonstrate the capabilities of the proposed model and compare it with existing baselines. We show that our method can synthesize physically plausible hair motion besides expression and camera control.

2026-04-07T21:09:52Z Project Page: see https://phys-head.github.io/; Youtube Video: see https://www.youtube.com/watch?v=k68fsSSwzc0; Accepted to CVPR 2026 Berna Kabadayi Vanessa Sklyarova Wojciech Zielonka Justus Thies Gerard Pons-Moll http://arxiv.org/abs/2604.05794v1 2026-04-07T12:30:19Z

Strand-level hair geometry reconstruction is a fundamental problem in virtual human modeling and the digitization of hairstyles. However, existing methods still suffer from a significant trade-off between accuracy and efficiency. Implicit neural representations can capture the global hair shape but often fail to preserve fine-grained strand details, while explicit optimization-based approaches achieve high-fidelity reconstructions at the cost of heavy computation and poor scalability. To address this issue, we propose EfficientMonoHair, a fast and accurate framework that combines the implicit neural network with multi-view geometric fusion for strand-level reconstruction from monocular video. Our method introduces a fusion-patch-based multi-view optimization that reduces the number of optimization iterations for point cloud direction, as well as a novel parallel hair-growing strategy that relaxes voxel occupancy constraints, allowing large-scale strand tracing to remain stable and robust even under inaccurate or noisy orientation fields. Extensive experiments on representative real-world hairstyles demonstrate that our method can robustly reconstruct high-fidelity strand geometries with accuracy. On synthetic benchmarks, our method achieves reconstruction quality comparable to state-of-the-art methods, while improving runtime efficiency by nearly an order of magnitude.

2026-04-07T12:30:19Z 10 pages, 6 figures, conference Da Li Dominik Engel Deng Luo Ivan Viola http://arxiv.org/abs/2604.03716v1 2026-04-04T12:44:08Z

We present a compact pipeline for high-fidelity hair reconstruction from multi-view images. While recent 3D Gaussian Splatting (3DGS) methods achieve realistic results, they often require millions of primitives, leading to high storage and rendering costs. Observing that hair exhibits structural and visual similarities across a hairstyle, we cluster strands into representative hair cards and group these into shared texture codebooks. Our approach integrates this structure with 3DGS rendering, significantly reducing reconstruction time and storage while maintaining comparable visual quality. In addition, we propose a generative prior accelerated method to reconstruct the initial strand geometry from a set of images. Our experiments demonstrate a 4-fold reduction in strand reconstruction time and achieve comparable rendering performance with over 200x lower memory footprint.

2026-04-04T12:44:08Z Accepted to CVPR 2026. This arXiv version is not the final published version Haimin Luo Srinjay Sarkar Albert Mosella-Montoro Francisco Vicente Carrasco Fernando De la Torre http://arxiv.org/abs/2604.02867v1 2026-04-03T08:35:35Z

Reconstructing strand-level 3D hair from a single-view image is highly challenging, especially when preserving consistent and realistic attributes in unseen regions. Existing methods rely on limited frontal-view cues and small-scale/style-restricted synthetic data, often failing to produce satisfactory results in invisible regions. In this work, we propose a novel framework that leverages the strong 3D priors of video generation models to transform single-view hair reconstruction into a calibrated multi-view reconstruction task. To balance reconstruction quality and efficiency for the reformulated multi-view task, we further introduce a neural orientation extractor trained on sparse real-image annotations for better full-view orientation estimation. In addition, we design a two-stage strand-growing algorithm based on a hybrid implicit field to synthesize the 3D strand curves with fine-grained details at a relatively fast speed. Extensive experiments demonstrate that our method achieves state-of-the-art performance on single-view 3D hair strand reconstruction on a diverse range of hair portraits in both visible and invisible regions.

2026-04-03T08:35:35Z 17 pages, 6 figures Leyang Jin Yujian Zheng Bingkui Tong Yuda Qiu Zhenyu Xie Hao Li http://arxiv.org/abs/2603.23345v1 2026-03-24T15:43:54Z

We present FHAvatar, a novel framework for reconstructing 3D Gaussian avatars with composable face and hair components from an arbitrary number of views. Unlike previous approaches that couple facial and hair representations within a unified modeling process, we explicitly decouple two components in texture space by representing the face with planar Gaussians and the hair with strand-based Gaussians. To overcome the limitations of existing methods that rely on dense multi-view captures or costly per-identity optimization, we propose an aggregated transformer backbone to learn geometry-aware cross-view priors and head-hair structural coherence from multi-view datasets, enabling effective and efficient feature extraction and fusion from few casual captures. Extensive quantitative and qualitative experiments demonstrate that FHAvatar achieves state-of-the-art reconstruction quality from only a few observations of new identities within minutes, while supporting real-time animation, convenient hairstyle transfer, and stylized editing, broadening the accessibility and applicability of digital avatar creation.

2026-03-24T15:43:54Z Yujie Sun Zhuoqiang Cai Chaoyue Niu Jianchuan Chen Zhiwen Chen Chengfei Lv Fan Wu http://arxiv.org/abs/2602.03749v1 2026-02-03T17:12:36Z

We introduce a framework that automates the transformation of static anime illustrations into manipulatable 2.5D models. Current professional workflows require tedious manual segmentation and the artistic ``hallucination'' of occluded regions to enable motion. Our approach overcomes this by decomposing a single image into fully inpainted, semantically distinct layers with inferred drawing orders. To address the scarcity of training data, we introduce a scalable engine that bootstraps high-quality supervision from commercial Live2D models, capturing pixel-perfect semantics and hidden geometry. Our methodology couples a diffusion-based Body Part Consistency Module, which enforces global geometric coherence, with a pixel-level pseudo-depth inference mechanism. This combination resolves the intricate stratification of anime characters, e.g., interleaving hair strands, allowing for dynamic layer reconstruction. We demonstrate that our approach yields high-fidelity, manipulatable models suitable for professional, real-time animation applications.

2026-02-03T17:12:36Z 23 pages, 20 figures, preprint version only Jian Lin Chengze Li Haoyun Qin Kwun Wang Chan Yanghua Jin Hanyuan Liu Stephen Chun Wang Choy Xueting Liu http://arxiv.org/abs/2601.09229v1 2026-01-14T07:02:21Z

Person identification in forensic investigations becomes very challenging when common identification means for DNA (i.e., hair strands, soft tissue) are not available. Current methods utilize deep learning methods for face recognition. However, these methods lack effective mechanisms to model cross-domain structural correspondence between two different forensic modalities. In this paper, we introduce a SPOT-Face, a superpixel graph-based framework designed for cross-domain forensic face identification of victims using their skeleton and sketch images. Our unified framework involves constructing a superpixel-based graph from an image and then using different graph neural networks(GNNs) backbones to extract the embeddings of these graphs, while cross-domain correspondence is established through attention-guided optimal transport mechanism. We have evaluated our proposed framework on two publicly available dataset: IIT\_Mandi\_S2F (S2F) and CUFS. Extensive experiments were conducted to evaluate our proposed framework. The experimental results show significant improvement in identification metrics ( i.e., Recall, mAP) over existing graph-based baselines. Furthermore, our framework demonstrates to be highly effective for matching skulls and sketches to faces in forensic investigations.

2026-01-14T07:02:21Z 14 pages, 5 figures, 3 tables (ICPR_2026) Ravi Shankar Prasad Dinesh Singh http://arxiv.org/abs/2512.17094v1 2025-12-18T21:45:45Z

The creation of photorealistic dynamic hair remains a major challenge in digital human modeling because of the complex motions, occlusions, and light scattering. Existing methods often resort to static capture and physics-based models that do not scale as they require manual parameter fine-tuning to handle the diversity of hairstyles and motions, and heavy computation to obtain high-quality appearance. In this paper, we present Dynamic Gaussian Hair (DGH), a novel framework that efficiently learns hair dynamics and appearance. We propose: (1) a coarse-to-fine model that learns temporally coherent hair motion dynamics across diverse hairstyles; (2) a strand-guided optimization module that learns a dynamic 3D Gaussian representation for hair appearance with support for differentiable rendering, enabling gradient-based learning of view-consistent appearance under motion. Unlike prior simulation-based pipelines, our approach is fully data-driven, scales with training data, and generalizes across various hairstyles and head motion sequences. Additionally, DGH can be seamlessly integrated into a 3D Gaussian avatar framework, enabling realistic, animatable hair for high-fidelity avatar representation. DGH achieves promising geometry and appearance results, providing a scalable, data-driven alternative to physics-based simulation and rendering.

2025-12-18T21:45:45Z Accepted by NeurIPS 2025. Project page: https://junyingw.github.io/paper/dgh Junying Wang Yuanlu Xu Edith Tretschk Ziyan Wang Anastasia Ianina Aljaz Bozic Ulrich Neumann Tony Tung http://arxiv.org/abs/2509.21541v4 2026-08-02T16:42:29Z

Hair simulation and rendering are challenging due to complex strand dynamics, diverse material properties, and intricate light-hair interactions. Recent video diffusion models can generate high-quality videos, but they lack fine-grained control over hair dynamics. We present ControlHair, a hybrid framework that integrates a physics simulator with conditional video diffusion to enable precise and controllable dynamic hair rendering. ControlHair adopts a three-stage pipeline: it first encodes physics conditions into per-frame geometry using a simulator, then extracts per-frame control signals, and finally feeds control signals into a video diffusion model to generate videos with desired hair dynamics. This cascaded design decouples physics reasoning from video generation, supports diverse physics, and makes training the video diffusion model easy. Trained on a curated 10K video dataset, ControlHair outperforms text- and pose-conditioned baselines, delivering precisely controlled hair dynamics. We also demonstrate three use cases of ControlHair, including dynamic hairstyle try-on, bullet-time effects, and cinemagraphic. Project page: https://linwk20.github.io/controlhair-web.

2025-09-25T20:29:05Z Accepted to ECCV 2026. 21 pages. Project page: https://linwk20.github.io/controlhair-web Weikai Lin Haoxiang Li Yuhao Zhu http://arxiv.org/abs/2509.21114v1 2025-09-25T13:00:38Z

We present CHARM, a novel parametric representation and generative framework for anime hairstyle modeling. While traditional hair modeling methods focus on realistic hair using strand-based or volumetric representations, anime hairstyle exhibits highly stylized, piecewise-structured geometry that challenges existing techniques. Existing works often rely on dense mesh modeling or hand-crafted spline curves, making them inefficient for editing and unsuitable for scalable learning. CHARM introduces a compact, invertible control-point-based parameterization, where a sequence of control points represents each hair card, and each point is encoded with only five geometric parameters. This efficient and accurate representation supports both artist-friendly design and learning-based generation. Built upon this representation, CHARM introduces an autoregressive generative framework that effectively generates anime hairstyles from input images or point clouds. By interpreting anime hairstyles as a sequential "hair language", our autoregressive transformer captures both local geometry and global hairstyle topology, resulting in high-fidelity anime hairstyle creation. To facilitate both training and evaluation of anime hairstyle generation, we construct AnimeHair, a large-scale dataset of 37K high-quality anime hairstyles with separated hair cards and processed mesh data. Extensive experiments demonstrate state-of-the-art performance of CHARM in both reconstruction accuracy and generation quality, offering an expressive and scalable solution for anime hairstyle modeling. Project page: https://hyzcluster.github.io/charm/

2025-09-25T13:00:38Z SIGGRAPH Asia 2025. 17 pages, 15 figures Yuze He Yanning Zhou Wang Zhao Jingwen Ye Yushi Bai Kaiwen Xiao Yong-Jin Liu Zhongqian Sun Wei Yang