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
@article{arxiv.2306.07632,
title = {NeuS-PIR: Learning Relightable Neural Surface using Pre-Integrated Rendering},
author = {Shi Mao and Chenming Wu and Zhelun Shen and Yifan Wang and Dayan Wu and Liangjun Zhang},
journal= {arXiv preprint arXiv:2306.07632},
year = {2024}
}