Learning a Delighting Prior for Facial Appearance Capture in the Wild

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Han, Yuxuan, Ming, Xin, Li, Tianxiao, Shen, Zhuofan, Zhang, Qixuan, Xu, Lan, Xu, Feng
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913097402286080
author Han, Yuxuan
Ming, Xin
Li, Tianxiao
Shen, Zhuofan
Zhang, Qixuan
Xu, Lan
Xu, Feng
author_facet Han, Yuxuan
Ming, Xin
Li, Tianxiao
Shen, Zhuofan
Zhang, Qixuan
Xu, Lan
Xu, Feng
contents High-quality facial appearance capture has traditionally required costly studio recording. Recent works consider an in-the-wild smartphone-based setup; however, their model-based inverse rendering paradigm struggles with the complex disentanglement of reflectance from unknown illumination. To bridge this gap, we propose to shift the paradigm into training a powerful delighting network as a prior to constrain the optimization. We leverage the OLAT dataset and the rendered Light Stage scans for training, and propose Dataset Latent Modulation (DLM) to seamlessly integrate these heterogeneous data sources. Specifically, by conditioning the core network on learnable source-aware tokens, we decouple dataset-specific styles from physical delighting principles, enabling the emergence of a delighting prior that outperforms existing proprietary models. This powerful delighting prior enables a simple and automatic appearance capture pipeline that achieves high-quality reflectance estimation from casual video inputs, outperforming prior arts by a large margin. Furthermore, we leverage our appearance capture method to transform the multi-view NeRSemble dataset into NeRSemble-Scan, a large-scale collection of 4K-resolution relightable scans. By open-sourcing our model and the NeRSemble-Scan dataset, we democratize high-end facial capture and provide a new foundation for the research community to build photorealistic digital humans.
format Preprint
id arxiv_https___arxiv_org_abs_2605_05636
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning a Delighting Prior for Facial Appearance Capture in the Wild
Han, Yuxuan
Ming, Xin
Li, Tianxiao
Shen, Zhuofan
Zhang, Qixuan
Xu, Lan
Xu, Feng
Computer Vision and Pattern Recognition
Graphics
High-quality facial appearance capture has traditionally required costly studio recording. Recent works consider an in-the-wild smartphone-based setup; however, their model-based inverse rendering paradigm struggles with the complex disentanglement of reflectance from unknown illumination. To bridge this gap, we propose to shift the paradigm into training a powerful delighting network as a prior to constrain the optimization. We leverage the OLAT dataset and the rendered Light Stage scans for training, and propose Dataset Latent Modulation (DLM) to seamlessly integrate these heterogeneous data sources. Specifically, by conditioning the core network on learnable source-aware tokens, we decouple dataset-specific styles from physical delighting principles, enabling the emergence of a delighting prior that outperforms existing proprietary models. This powerful delighting prior enables a simple and automatic appearance capture pipeline that achieves high-quality reflectance estimation from casual video inputs, outperforming prior arts by a large margin. Furthermore, we leverage our appearance capture method to transform the multi-view NeRSemble dataset into NeRSemble-Scan, a large-scale collection of 4K-resolution relightable scans. By open-sourcing our model and the NeRSemble-Scan dataset, we democratize high-end facial capture and provide a new foundation for the research community to build photorealistic digital humans.
title Learning a Delighting Prior for Facial Appearance Capture in the Wild
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2605.05636