GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling
This addresses the challenge for computer graphics and visual effects professionals who need realistic and editable hair models, though it is an incremental improvement over existing hair capture methods.
The paper tackles the problem of creating relightable hair appearance models from multi-view images by developing GroomLight, a hybrid inverse rendering method that combines an extended hair BSDF model with a light-aware residual model, achieving state-of-the-art performance in high-fidelity relighting, view synthesis, and material editing.
We present GroomLight, a novel method for relightable hair appearance modeling from multi-view images. Existing hair capture methods struggle to balance photorealistic rendering with relighting capabilities. Analytical material models, while physically grounded, often fail to fully capture appearance details. Conversely, neural rendering approaches excel at view synthesis but generalize poorly to novel lighting conditions. GroomLight addresses this challenge by combining the strengths of both paradigms. It employs an extended hair BSDF model to capture primary light transport and a light-aware residual model to reconstruct the remaining details. We further propose a hybrid inverse rendering pipeline to optimize both components, enabling high-fidelity relighting, view synthesis, and material editing. Extensive evaluations on real-world hair data demonstrate state-of-the-art performance of our method.