PhysHead: Simulation-Ready Gaussian Head Avatars

• URL: http://arxiv.org/abs/2604.06467v1
• Date: Tue, 07 Apr 2026 21:09:52 GMT
• Title: PhysHead: Simulation-Ready Gaussian Head Avatars
• Abstract summary: 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.
• Score: 41.929095478168406
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Head Avatars with Dynamic Explicit Hair [131.7147763902007]
  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.
  arXiv  Detail & Related papers  (2026-07-26T22:08:13Z)
• 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)
• 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)
• 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)
• SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing [59.44721317364197]
  We introduce SimAvatar, a framework designed to generate simulation-ready clothed 3D human avatars from a text prompt.<n>Our method is the first to produce highly realistic, fully simulation-ready 3D avatars, surpassing the capabilities of current approaches.
  arXiv  Detail & Related papers  (2024-12-12T18:35:26Z)
• GaussianHeads: End-to-End Learning of Drivable Gaussian Head Avatars from Coarse-to-fine Representations [54.94362657501809]
  We propose a new method to generate highly dynamic and deformable human head avatars from multi-view imagery in real-time. At the core of our method is a hierarchical representation of head models that allows to capture the complex dynamics of facial expressions and head movements. We train this coarse-to-fine facial avatar model along with the head pose as a learnable parameter in an end-to-end framework.
  arXiv  Detail & Related papers  (2024-09-18T13:05:43Z)
• 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)
• Text-Guided Generation and Editing of Compositional 3D Avatars [59.584042376006316]
  Our goal is to create a realistic 3D facial avatar with hair and accessories using only a text description. Existing methods either lack realism, produce unrealistic shapes, or do not support editing.
  arXiv  Detail & Related papers  (2023-09-13T17:59:56Z)
• 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.