Recent advances in implicit neural representation have demonstrated the ability to recover detailed geometry and material from multi-view images. However, the use of simplified lighting models such as environment maps to represent non-distant illumination, or using a network to fit indirect light modeling without a solid basis, can lead to an undesirable decomposition between lighting and material. To address this, we propose a fully differentiable framework named neural ambient illumination (NeAI) that uses Neural Radiance Fields (NeRF) as a lighting model to handle complex lighting in a physically based way. Together with integral lobe encoding for roughness-adaptive specular lobe and leveraging the pre-convoluted background for accurate decomposition, the proposed method represents a significant step towards integrating physically based rendering into the NeRF representation. The experiments demonstrate the superior performance of novel-view rendering compared to previous works, and the capability to re-render objects under arbitrary NeRF-style environments opens up exciting possibilities for bridging the gap between virtual and real-world scenes. The project and supplementary materials are available at https://yiyuzhuang.github.io/NeAI/.
@article{arxiv.2304.08757,
title = {NeAI: A Pre-convoluted Representation for Plug-and-Play Neural Ambient Illumination},
author = {Yiyu Zhuang and Qi Zhang and Xuan Wang and Hao Zhu and Ying Feng and Xiaoyu Li and Ying Shan and Xun Cao},
journal= {arXiv preprint arXiv:2304.08757},
year = {2023}
}