GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zheng, Yang, Chai, Menglei, Vicini, Delio, Zhou, Yuxiao, Xu, Yinghao, Guibas, Leonidas, Wetzstein, Gordon, Beeler, Thabo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917956271734784
author Zheng, Yang
Chai, Menglei
Vicini, Delio
Zhou, Yuxiao
Xu, Yinghao
Guibas, Leonidas
Wetzstein, Gordon
Beeler, Thabo
author_facet Zheng, Yang
Chai, Menglei
Vicini, Delio
Zhou, Yuxiao
Xu, Yinghao
Guibas, Leonidas
Wetzstein, Gordon
Beeler, Thabo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10597
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling
Zheng, Yang
Chai, Menglei
Vicini, Delio
Zhou, Yuxiao
Xu, Yinghao
Guibas, Leonidas
Wetzstein, Gordon
Beeler, Thabo
Graphics
Computer Vision and Pattern Recognition
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.
title GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.10597