(The Eurographics Association, 2024) Su, Xiongfei; Zhu, Tianyi; Liu, Lina; Zhang, Yuanlong; Chen, Renjie; Ritschel, Tobias; Whiting, Emily
The field of non-line-of-sight (NLOS) imaging is experiencing rapid advancement, offering the potential to reveal hidden scenes that are otherwise obscured from direct view. Despite this promise, NLOS systems face obstacles in managing a variety of sampling noise, as well as spatial and temporal variations, which limit their practical deployment. This paper introduces a novel strategy to overcome these challenges. It employs prompts to encode latent information, which is then leveraged to dynamically guide the NLOS reconstruction network. The proposed method, P-NLOS, consists of two branches: a reconstruction branch that handles the restoration of sampled information, and a prompting branch that captures the original information. The prompting branch supplies reliable content to the reconstruction branch, thereby enhancing the guidance of the reconstruction process and enhancing the quality of the recovered images. Overall, P-NLOS demonstrates robustness in real-world applications by effectively handling a wide range of corruption types in NLOS reconstruction tasks, including varying noise levels, diverse blur kernels, and temporal resolution variations.