L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing
Abstract
We introduce a highly efficient light visibility estimation method, called L-Tracing, for reflectance factorization on neural implicit surfaces. Light visibility is indispensable for modeling shadows and specular of high quality on object’s surface. For neural implicit representations, former methods of computing light visibility suffer from efficiency and quality drawbacks. L-Tracing leverages the distance meaning of the Signed Distance Function(SDF), and computes the light visibility of the solid object surface according to binary geometry occlusions. We prove the linear convergence of L-Tracing algorithm and give out the theoretical lower bound of tracing iteration. Based on L-Tracing, we propose a new surface reconstruction and reflectance factorization framework. Experiments show our framework performs nearly 10x speedup on factorization, and achieves competitive albedo and relighting results with existing approaches.
Cite
Text
Chen et al. "L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-19784-0_13Markdown
[Chen et al. "L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/chen2022eccv-ltracing/) doi:10.1007/978-3-031-19784-0_13BibTeX
@inproceedings{chen2022eccv-ltracing,
title = {{L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing}},
author = {Chen, Ziyu and Ding, Chenjing and Guo, Jianfei and Wang, Dongliang and Li, Yikang and Xiao, Xuan and Wu, Wei and Song, Li},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2022},
doi = {10.1007/978-3-031-19784-0_13},
url = {https://mlanthology.org/eccv/2022/chen2022eccv-ltracing/}
}