English

DGH: Dynamic Gaussian Hair

Computer Vision and Pattern Recognition 2025-12-22 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2512.17094,
  title  = {DGH: Dynamic Gaussian Hair},
  author = {Junying Wang and Yuanlu Xu and Edith Tretschk and Ziyan Wang and Anastasia Ianina and Aljaz Bozic and Ulrich Neumann and Tony Tung},
  journal= {arXiv preprint arXiv:2512.17094},
  year   = {2025}
}

Comments

Accepted by NeurIPS 2025. Project page: https://junyingw.github.io/paper/dgh

R2 v1 2026-07-01T08:32:35.885Z