Physics-based inverse rendering enables joint optimization of shape, material, and lighting based on captured 2D images. To ensure accurate reconstruction, using a light model that closely resembles the captured environment is essential. Although the widely adopted distant environmental lighting model is adequate in many cases, we demonstrate that its inability to capture spatially varying illumination can lead to inaccurate reconstructions in many real-world inverse rendering scenarios. To address this limitation, we incorporate NeRF as a non-distant environment emitter into the inverse rendering pipeline. Additionally, we introduce an emitter importance sampling technique for NeRF to reduce the rendering variance. Through comparisons on both real and synthetic datasets, our results demonstrate that our NeRF-based emitter offers a more precise representation of scene lighting, thereby improving the accuracy of inverse rendering.

• Paper: pdf (12 MB)
• Source code: coming soon!

@inproceedings{Ling:2024:PBIR-NeRF,
  title={NeRF As A Non-Distant Environment Emitter in Physics-Based Inverse Rendering},
  author={Ling, J. and Yu, R. and Xu, F. and Du, C. and Zhao, S.},
  booktitle = {ACM SIGGRAPH 2024 Conference Proceedings},
  year = {2024},
}

This work was supported by the National Key R&D Program of China (2023YFC3305600, 2018YFA0704000), the NSFC (No.62021002), and the Key Research and Development Project of Tibet Autonomous Region (XZ202101ZY0019G). This work was also supported by THUIBCS, Tsinghua University, and BLBCI, Beijing Municipal Education Commission.