Fast Non-Line-Of-Sight Imaging with Two-Step Deep Remapping
journal contributionposted on 2022-06-03, 20:45 authored by Dayu Zhu, Wenshan Cai
Conventional imaging only records the photons directly sent from the object to the detector, whereas 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, transient detection requires sophisticated apparatus, long scanning time, and low robustness to the ambient environment, and the reconstruction algorithms are typically time consuming and computationally expensive. Here, we propose a new NLOS solution with innovations on both equipment and algorithm. We apply inexpensive Lidar for detection, with much higher scanning speed and better compatibility to real-world imaging. Our reconstruction framework is deep learning based, with generative two-step remapping strategy to guarantee high reconstruction fidelity. The overall detection and reconstruction process allows for millisecond responses, with state-of-the-art reconstruction performance. We have experimentally tested the proposed solution on both synthetic and real objects and further demonstrated our method to be applicable for full-color NLOS imaging.
Read the peer-reviewed publication
typically time consumingtransient scanning processstep remapping strategyphotons directly sentlong scanning timeapply inexpensive lidarreconstruction process allowsdeep learning basedart reconstruction performancenlos solutions employnew nlos solutioncolor nlos imagingreconstruction frameworkreconstruction algorithmsproposed solutionnlos scenesworld imagingimaging takeswhereas nonmillisecond responseslow robustnessindirect lightfast nonexperimentally testedcomputationally expensivebetter compatibilitybased algorithmambient environment