Fast Non-line-of-sight Imaging with Two-step Deep Remapping
This work addresses the limitations of conventional NLOS imaging for applications requiring fast and robust scene reconstruction, though it appears incremental by combining existing technologies in a novel way.
The paper tackles the problem of slow and expensive non-line-of-sight imaging by proposing a solution using inexpensive commercial Lidar and a deep learning-based reconstruction framework, achieving millisecond response times and millimeter-level precision.
Conventional imaging only records photons directly sent from the object to the detector, while non-line-of-sight (NLOS) imaging takes the indirect light into account. Most NLOS solutions employ a transient scanning process, followed by a physical based algorithm to reconstruct the NLOS scenes. However, the transient detection requires sophisticated apparatus, with long scanning time and low robustness to ambient environment, and the reconstruction algorithms are typically time-consuming and computationally expensive. Here we propose a new NLOS solution to address the above defects, with innovations on both equipment and algorithm. We apply inexpensive commercial Lidar for detection, with much higher scanning speed and better compatibility to real-world imaging. Our reconstruction framework is deep learning based, with a generative two-step remapping strategy to guarantee high reconstruction fidelity. The overall detection and reconstruction process allows for millisecond responses, with reconstruction precision of millimeter level. We have experimentally tested the proposed solution on both synthetic and real objects, and further demonstrated our method to be applicable to full-color NLOS imaging.