2022
DOI: 10.48550/arxiv.2205.01679
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Physics to the Rescue: Deep Non-line-of-sight Reconstruction for High-speed Imaging

Abstract: Computational approach to imaging around the corner, or non-line-of-sight (NLOS) imaging, is becoming a reality thanks to major advances in imaging hardware and reconstruction algorithms. A recent development towards practical NLOS imaging, Nam et al.[1] demonstrated a high-speed non-confocal imaging system that operates at 5Hz, 100x faster than the prior art. This enormous gain in acquisition rate, however, necessitates numerous approximations in light transport, breaking many existing NLOS reconstruction met… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 38 publications
0
1
0
Order By: Relevance
“…A Fourier-based loss excels when the rendered and observed histograms are very different, but may not provide as strong of a signal when they are similar. We adapt Mu et al's Python implementation [25] of the algorithm given by Urea et al [26] to uniformly sample rays from the rectangular FoV of the TMF8820.…”
Section: E Inter-histogram Interferencementioning
confidence: 99%
“…A Fourier-based loss excels when the rendered and observed histograms are very different, but may not provide as strong of a signal when they are similar. We adapt Mu et al's Python implementation [25] of the algorithm given by Urea et al [26] to uniformly sample rays from the rectangular FoV of the TMF8820.…”
Section: E Inter-histogram Interferencementioning
confidence: 99%