Physics to the Rescue: Deep Non-Line-of-Sight Reconstruction for High-Speed Imaging
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-08 · 47 (8) · 6146-6158
DOI: 10.1109/tpami.2022.3203383 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-08. Verfasst von Fangzhou Mu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: DARPA REVEAL Project, University of Wisconsin-Madison Office of the Vice Chancellor for Research and Graduate Education through Wisconsin Alumni Research Foundation.
Abstract (Originalsprache)
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. 2021) 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 methods that assume an idealized image formation model. To bridge the gap, we present a novel deep model that incorporates the complementary physics priors of wave propagation and volume rendering into a neural network for high-quality and robust NLOS reconstruction. This orchestrated design regularizes the solution space by relaxing the image formation model, resulting in a deep model that generalizes well on real captures despite being exclusively trained on synthetic data. Further, we devise a unified learning framework that enables our model to be flexibly trained using diverse supervision signals, including target intensity images or even raw NLOS transient measurements. Once trained, our model renders both intensity and depth images at inference time in a single forward pass, capable of processing more than 5 captures per second on a high-end GPU. Through extensive qualitative and quantitative experiments, we show that our method outperforms prior physics and learning based approaches on both synthetic and real measurements. We anticipate that our method along with the fast capturing system will accelerate future development of NLOS imaging for real world applications that require high-speed imaging.
Förderung
- DARPA REVEAL Project
- University of Wisconsin-Madison Office of the Vice Chancellor for Research and Graduate Education through Wisconsin Alumni Research Foundation
Zitieren
APA
Mu, F., Mo, S., Peng, J., Liu, X., Nam, J. H., Raghavan, S., Velten, A., & Li, Y. (2025). Physics to the Rescue: Deep Non-Line-of-Sight Reconstruction for High-Speed Imaging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(8), 6146-6158. https://doi.org/10.1109/tpami.2022.3203383
Vancouver
Mu F, Mo S, Peng J, Liu X, Nam JH, Raghavan S, et al. Physics to the Rescue: Deep Non-Line-of-Sight Reconstruction for High-Speed Imaging. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(8):6146-6158. doi:10.1109/tpami.2022.3203383
BibTeX
@article{Mu2025,
author = {Mu, Fangzhou and Mo, Sicheng and Peng, Jiayong and Liu, Xiaochun and Nam, Ji Hyun and Raghavan, Siddeshwar and Velten, Andreas and Li, Yin},
title = {Physics to the Rescue: Deep Non-Line-of-Sight Reconstruction for High-Speed Imaging},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {8},
pages = {6146--6158},
doi = {10.1109/tpami.2022.3203383}
}
EUVIMED