Hyper-NLOS: hyperspectral passive non-line-of-sight imaging

Abstract

Passive non-line-of-sight (NLOS) imaging has potential applications in autonomous driving and search and rescue, but current deep learning approaches often produce suboptimal images due to sparse and homogeneous projection features, leading to an ill-posed reconstruction process. To address this, we propose the Hyperspectral Fusion NLOS imaging technique (HFN-Net), which first leverages high-dimensional features from multiple spectra and incorporates spatial-spectral attention from a hyperspectral full-color auto-encoder. This method improves color fidelity and structural details by fully utilizing the limited information and increasing feature diversity. Additionally, we developed the Hyperspectral NLOS dataset (HS-NLOS) for training and evaluation. Experimental results show that HFN-Net offers performance improvements over traditional passive NLOS 2D imaging techniques, emphasizing the importance of multi-spectral information.