Head Avatars with Dynamic Explicit Hair

• URL: http://arxiv.org/abs/2607.23861v1
• Date: Sun, 26 Jul 2026 22:08:13 GMT
• Title: Head Avatars with Dynamic Explicit Hair
• Abstract summary: We present DynHair, a novel method for tracking and modeling dynamic hair for human head avatars.<n>We reconstruct a dynamic head avatar with an explicit strand-based hair representation using structured 3D Gaussian Splatting.<n>As a result of our method, we retrieve hair tracking of the training video data and an animatable head avatar with controllable hair dynamics.
• Score: 131.7147763902007
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• AvatarDynamizer: From Static to Dynamic Human Avatars via Generative Dynamic Textures [81.30642929096783]
  AvatarDynamizer is a generative method that transforms an off-the-shelf static 3D avatar into a controllable, realistic, and multi-view-consistent 4D avatar.<n>Our method effectively animates static avatars with faithful surface dynamics and outperforms competing generalizable methods in visual fidelity.
  arXiv  Detail & Related papers  (2026-08-20T11:10:53Z)
• One-shot Compositional 3D Head Avatars with Deformable Hair [24.96145773116589]
  We propose a compositional method for constructing a complete 3D head avatar from a single image.<n>Our method explicitly decouples hair from the face, modeling these components using distinct deformation paradigms.<n>By leveraging image-to-3D lifting techniques, we preserve fine-grained textures from the input image to the greatest extent possible.
  arXiv  Detail & Related papers  (2026-04-16T08:39:37Z)
• PhysHead: Simulation-Ready Gaussian Head Avatars [41.929095478168406]
  We introduce PhysHead, a hybrid representation for animatable head avatars with realistic hair dynamics.<n>Our approach combines a 3D parametric mesh for the head with strand-based hair, which can be directly simulated using physics engines.<n>We show that our method can synthesize physically plausible hair motion besides expression and camera control.
  arXiv  Detail & Related papers  (2026-04-07T21:09:52Z)
• DGH: Dynamic Gaussian Hair [34.04732593280566]
  We present Dynamic Gaussian Hair (DGH), a novel framework that efficiently learns hair dynamics and appearance.<n>DGH achieves promising geometry and appearance results, providing a scalable, data-driven alternative to physics-based simulation and rendering.
  arXiv  Detail & Related papers  (2025-12-18T21:45:45Z)
• HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars [29.819374818200885]
  We present a universal prior model for 3D head avatars with explicit hair compositionality.<n>Our model's inherent compositionality enables seamless transfer of face and hair components between avatars.
  arXiv  Detail & Related papers  (2025-07-25T17:59:53Z)
• TeGA: Texture Space Gaussian Avatars for High-Resolution Dynamic Head Modeling [52.87836237427514]
  Photoreal avatars are seen as a key component in emerging applications in telepresence, extended reality, and entertainment.<n>We present a new high-detail 3D head avatar model that improves upon the state of the art.
  arXiv  Detail & Related papers  (2025-05-08T22:10:27Z)
• LUCAS: Layered Universal Codec Avatars [48.737625335705644]
  Photo 3D head avatar reconstruction faces critical challenges in modeling dynamic face-hair interactions.<n>We present LUCAS, a novel Universal Prior Model (UPM) for avatar modeling that disentangles face and hair through a layered representation.
  arXiv  Detail & Related papers  (2025-02-27T04:07:27Z)
• HHAvatar: Gaussian Head Avatar with Dynamic Hairs [27.20228210350169]
  We proposeAvatar represented by controllable 3D Gaussians for high-fidelity head avatar with dynamic hair modeling. Our approach outperforms other state-of-the-art sparse-view methods, achieving ultra high-fidelity rendering quality at 2K resolution.
  arXiv  Detail & Related papers  (2023-12-05T11:01:44Z)
• GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians [51.46168990249278]
  We present an efficient approach to creating realistic human avatars with dynamic 3D appearances from a single video. GustafAvatar is validated on both the public dataset and our collected dataset.
  arXiv  Detail & Related papers  (2023-12-04T18:55:45Z)
• NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation [23.625243364572867]
  The capture and animation of human hair are two of the major challenges in the creation of realistic avatars for the virtual reality. We present a two-stage approach that models hair independently from the head to address these challenges in a data-driven manner. Our model outperforms the state of the art in novel view synthesis and is capable of creating novel hair animations without having to rely on hair observations as a driving signal.
  arXiv  Detail & Related papers  (2022-12-01T16:09:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.