TransDiff: Unsupervised Non-Line-of-Sight Imaging With Aperture-Limited Relay Surfaces
IEEE Transactions on Image Processing · 2025 · 34 · 8018-8031
DOI: 10.1109/tip.2025.3637694 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Xingyu Cui und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Non-line-of-sight (NLOS) imaging aims to reconstruct scenes hidden from direct view and has broad applications in robotic vision, rescue operations, autonomous driving, and remote sensing. However, most existing methods rely on densely sampled transients from large, continuous relay surfaces, which limits their practicality in real-world scenarios with aperture constraints. To address this limitation, we propose an unsupervised zero-shot framework tailored for confocal NLOS imaging with aperture-limited relay surfaces. Our method leverages latent diffusion models to recover fully-sampled transients from undersampled versions by enforcing measurement consistency during the sampling process. To further improve recovered transient quality, we introduce a progressive recovery strategy that incrementally recovers missing transient values, effectively mitigating the impact of severe aperture limitations. In addition, to suppress error propagation during recovery, we develop a backpropagation-based error correction reconstruction algorithm that refines intermediate recovered transients by enforcing sparsity regularization in the voxel domain, enabling high-fidelity final reconstructions. Extensive experiments on both simulated and real-world datasets validate the robustness and generalization capability of our method across diverse aperture-limited relay surfaces. Notably, our method follows a zero-shot paradigm, requiring only a single pretraining stage without paired data or pattern-specific retraining, which makes it a more practical and generalizable framework for NLOS imaging.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Cui, X., Yue, H., Sun, S., Li, Y., Hou, Y., Xiong, Z., & Yang, J. (2025). TransDiff: Unsupervised Non-Line-of-Sight Imaging With Aperture-Limited Relay Surfaces. IEEE Transactions on Image Processing, 34, 8018-8031. https://doi.org/10.1109/tip.2025.3637694
Vancouver
Cui X, Yue H, Sun S, Li Y, Hou Y, Xiong Z, et al. TransDiff: Unsupervised Non-Line-of-Sight Imaging With Aperture-Limited Relay Surfaces. IEEE Transactions on Image Processing. 2025;34:8018-8031. doi:10.1109/tip.2025.3637694
BibTeX
@article{Cui2025,
author = {Cui, Xingyu and Yue, Huanjing and Sun, Shida and Li, Yue and Hou, Yusen and Xiong, Zhiwei and Yang, Jingyu},
title = {TransDiff: Unsupervised Non-Line-of-Sight Imaging With Aperture-Limited Relay Surfaces},
journal = {IEEE Transactions on Image Processing},
year = {2025},
volume = {34},
pages = {8018--8031},
doi = {10.1109/tip.2025.3637694}
}
EUVIMED