NeuS-PIR: Learning Relightable Neural Surface using Pre-Integrated Rendering

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mao, Shi, Wu, Chenming, Shen, Zhelun, Wang, Yifan, Wu, Dayan, Zhang, Liangjun
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909149628989440
author Mao, Shi
Wu, Chenming
Shen, Zhelun
Wang, Yifan
Wu, Dayan
Zhang, Liangjun
author_facet Mao, Shi
Wu, Chenming
Shen, Zhelun
Wang, Yifan
Wu, Dayan
Zhang, Liangjun
contents This paper presents a method, namely NeuS-PIR, for recovering relightable neural surfaces using pre-integrated rendering from multi-view images or video. Unlike methods based on NeRF and discrete meshes, our method utilizes implicit neural surface representation to reconstruct high-quality geometry, which facilitates the factorization of the radiance field into two components: a spatially varying material field and an all-frequency lighting representation. This factorization, jointly optimized using an adapted differentiable pre-integrated rendering framework with material encoding regularization, in turn addresses the ambiguity of geometry reconstruction and leads to better disentanglement and refinement of each scene property. Additionally, we introduced a method to distil indirect illumination fields from the learned representations, further recovering the complex illumination effect like inter-reflection. Consequently, our method enables advanced applications such as relighting, which can be seamlessly integrated with modern graphics engines. Qualitative and quantitative experiments have shown that NeuS-PIR outperforms existing methods across various tasks on both synthetic and real datasets. Source code is available at https://github.com/Sheldonmao/NeuSPIR
format Preprint
id arxiv_https___arxiv_org_abs_2306_07632
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle NeuS-PIR: Learning Relightable Neural Surface using Pre-Integrated Rendering
Mao, Shi
Wu, Chenming
Shen, Zhelun
Wang, Yifan
Wu, Dayan
Zhang, Liangjun
Computer Vision and Pattern Recognition
Graphics
This paper presents a method, namely NeuS-PIR, for recovering relightable neural surfaces using pre-integrated rendering from multi-view images or video. Unlike methods based on NeRF and discrete meshes, our method utilizes implicit neural surface representation to reconstruct high-quality geometry, which facilitates the factorization of the radiance field into two components: a spatially varying material field and an all-frequency lighting representation. This factorization, jointly optimized using an adapted differentiable pre-integrated rendering framework with material encoding regularization, in turn addresses the ambiguity of geometry reconstruction and leads to better disentanglement and refinement of each scene property. Additionally, we introduced a method to distil indirect illumination fields from the learned representations, further recovering the complex illumination effect like inter-reflection. Consequently, our method enables advanced applications such as relighting, which can be seamlessly integrated with modern graphics engines. Qualitative and quantitative experiments have shown that NeuS-PIR outperforms existing methods across various tasks on both synthetic and real datasets. Source code is available at https://github.com/Sheldonmao/NeuSPIR
title NeuS-PIR: Learning Relightable Neural Surface using Pre-Integrated Rendering
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2306.07632