ControlHair: Synergizing Physics Simulator and Video Diffusion for Controllable Dynamic Hair Rendering

Summary · qwen2.5:32b

ControlHair introduces a hybrid framework integrating physics simulation with video diffusion to achieve precise control over dynamic hair rendering, addressing the limitations of current video diffusion models in controlling hair dynamics. This method decouples physics reasoning from video generation through a three-stage pipeline and outperforms text- and pose-conditioned baselines, as demonstrated using a curated dataset of 10K videos. The framework showcases applications such as dynamic hairstyle try-on and cinemagraphic effects.

Suggested post angle

Discover the new ControlHair framework that synergizes physics simulator and video diffusion for controllable dynamic hair rendering in real-time.

Excerpt

arXiv:2509.21541v3 Announce Type: replace Abstract: 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.