Non-Line-of-Sight Surface Reconstruction Using the Directional Light-Cone Transform
Abstract
We propose a joint albedo-normal approach to non-line-of-sight (NLOS) surface reconstruction using the directional light-cone transform (D-LCT). While current NLOS imaging methods reconstruct either the albedo or surface normals of the hidden scene, the two quantities provide complementary information of the scene, so an efficient method to estimate both simultaneously is desirable. We formulate the recovery of the two quantities as a vector deconvolution problem, and solve it via Cholesky-Wiener decomposition. We demonstrate that surfaces fitted non-parametrically using our recovered normals are more accurate than those produced with NLOS surface reconstruction methods recently proposed, and are 1,000 times faster to compute than using inverse rendering.
Cite
Text
Young et al. "Non-Line-of-Sight Surface Reconstruction Using the Directional Light-Cone Transform." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.00148Markdown
[Young et al. "Non-Line-of-Sight Surface Reconstruction Using the Directional Light-Cone Transform." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/young2020cvpr-nonlineofsight/) doi:10.1109/CVPR42600.2020.00148BibTeX
@inproceedings{young2020cvpr-nonlineofsight,
title = {{Non-Line-of-Sight Surface Reconstruction Using the Directional Light-Cone Transform}},
author = {Young, Sean I. and Lindell, David B. and Girod, Bernd and Taubman, David and Wetzstein, Gordon},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2020},
doi = {10.1109/CVPR42600.2020.00148},
url = {https://mlanthology.org/cvpr/2020/young2020cvpr-nonlineofsight/}
}