TY - GEN
T1 - Non-line-of-sight surface reconstruction using the directional light-cone transform
AU - Young, Sean I.
AU - Lindell, David B.
AU - Girod, Bernd
AU - Taubman, David
AU - Wetzstein, Gordon
N1 - KAUST Repository Item: Exported on 2022-06-30
Acknowledgements: We thank M. J. Galindo for help with dataset [53] and I. Gkioulekas for the code of [18, 19]. D.L. was supported by a Stanford Graduate Fellowship. G.W. was supported by an NSF CAREER Award (IIS 1553333), a Sloan Fellowship, by the KAUST Office of Sponsored Research through the Visual Computing Center CCF grant, the DARPA REVEAL program, and a PECASE by the ARL .
This publication acknowledges KAUST support, but has no KAUST affiliated authors.
PY - 2020/8/5
Y1 - 2020/8/5
N2 - 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.
AB - 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.
UR - http://hdl.handle.net/10754/679501
UR - https://ieeexplore.ieee.org/document/9157161/
UR - http://www.scopus.com/inward/record.url?scp=85090390410&partnerID=8YFLogxK
U2 - 10.1109/CVPR42600.2020.00148
DO - 10.1109/CVPR42600.2020.00148
M3 - Conference contribution
SP - 1404
EP - 1413
BT - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PB - IEEE
ER -