@article{Mao2025, 
author = {Shi Mao and Chenming Wu and Zhelun Shen and Yifan Wang and Dayan Wu and Liangjun Zhang},
title = {NeuS-PIR: Learning relightable neural surface using pre-integrated rendering},
year = {2025},
journal = {Computational Visual Media},
volume = {11},
number = {4},
pages = {727-744},
keywords = {inverse rendering, pre-integrated rendering, neural implicit representation},
url = {https://www.sciopen.com/article/10.26599/CVM.2025.9450493},
doi = {10.26599/CVM.2025.9450493},
abstract = {In this paper, we propose NeuS-PIR, a novel approach for learning relightable neural surfaces using pre-integrated rendering from multi-view image observations. Unlike traditional methods based on NeRFs or discrete mesh representations, our approach employs an implicit neural surface representation to reconstruct high-quality geometry. This representation enables the factorization of the radiance field into two components: a spatially varying material field and an all-frequency lighting model. By jointly optimizing this factorization with a differentiable pre-integrated rendering framework, and material encoding regularization, our method effectively addresses the ambiguity in geometry reconstruction, leading to improved disentanglement and refinement of scene properties. Furthermore, we introduce a technique to distill indirect illumination fields, capturing complex lighting effects such as inter-reflections. As a result, NeuS-PIR enables advanced applications like relighting, which can be seamlessly integrated into modern graphics engines. Extensive qualitative and quantitative experiments on both synthetic and real datasets demonstrate that NeuS-PIR outperforms existing methods across various tasks. Source code is available at https://github.com/Sheldonmao/NeuSPIR.}
}