NLOS-R: Alternate Reconstruction and Recognition for Non-Line-of-Sight Understanding

Download PDF
Open Webpage

Yi Wang, Ruixu Geng, Jiarui Zhang, Xiaolong Du, Yan Chen, Yang Hu

Published: 2025, Last Modified: 19 Jan 2026ICME 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Passive non-line-of-sight (NLOS) imaging aims to recover hidden scenes from indirect reflections. While reconstruction has been extensively studied, the high-level tasks for understanding hidden scenes, such as recognition, remain insufficiently explored despite their importance for practical applications. Direct classifying using either the projection or reconstructed images yields limited performance due to the severe image degradation. In this paper, we propose NLOS-R2, an alternate reconstruction-recognition framework that leverages the complementary nature of both tasks to enhance NLOS scene understanding. By iteratively optimizing reconstruction and recognition networks, our framework effectively improves recognition accuracy while maintaining reconstruction quality. To enable systematic evaluation, we introduce the first large-scale multi-class passive NLOS dataset, containing 42 classes and 50,400 projection and hidden image pairs. Extensive experiments demonstrate that our approach achieves 52.88% recognition accuracy, significantly outperforming existing methods. The code and dataset are available at https://github.com/ustceewy/NLOS-R2.