GroomCap: High-Fidelity Prior-Free Hair Capture
Yuxiao Zhou, Menglei Chai, Daoye Wang, Sebastian Winberg, Erroll Wood,, Kripasindhu Sarkar, Markus Gross, Thabo Beeler

TL;DR
GroomCap introduces a novel multi-view hair capture method that achieves high-fidelity, strand-level hair geometry reconstruction without external priors, using neural implicit representations and a Gaussian-based optimization.
Contribution
It presents a new neural implicit hair volume representation and a Gaussian-based refinement strategy that improve hair reconstruction fidelity without relying on external data priors.
Findings
Produces more precise and detailed hair geometries than existing methods.
Capable of capturing high-quality hair structures suitable for various applications.
Effectively prevents structural information loss through a novel orientation rendering algorithm.
Abstract
Despite recent advances in multi-view hair reconstruction, achieving strand-level precision remains a significant challenge due to inherent limitations in existing capture pipelines. We introduce GroomCap, a novel multi-view hair capture method that reconstructs faithful and high-fidelity hair geometry without relying on external data priors. To address the limitations of conventional reconstruction algorithms, we propose a neural implicit representation for hair volume that encodes high-resolution 3D orientation and occupancy from input views. This implicit hair volume is trained with a new volumetric 3D orientation rendering algorithm, coupled with 2D orientation distribution supervision, to effectively prevent the loss of structural information caused by undesired orientation blending. We further propose a Gaussian-based hair optimization strategy to refine the traced hair strands…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
