Fast Non-line-of-sight Imaging with Two-step Deep Remapping

TL;DR

This paper introduces a fast, high-precision non-line-of-sight imaging method using inexpensive Lidar and a deep learning reconstruction framework, enabling millisecond response times and full-color imaging.

Contribution

The authors propose a novel NLOS imaging approach combining commercial Lidar detection with a deep learning-based two-step remapping for rapid, high-fidelity scene reconstruction.

Findings

Achieves millisecond response times in NLOS imaging.

Provides millimeter-level reconstruction accuracy.

Demonstrates applicability to full-color NLOS imaging.

Abstract

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.