Non-line-of-sight (NLOS) imaging has the ability to recover 3D images of scenes outside the direct line of sight, which is of growing interest for diverse applications. Despite the remarkable progress, NLOS imaging of dynamic objects is still challenging. It requires a large amount of multibounce photons for the reconstruction of single-frame data. To overcome this obstacle, we develop a computational framework for dynamic time-of-flight NLOS imaging based on plug-and-play (PnP) algorithms. By combining imaging forward model with the deep denoising network from the computer vision community, we show a 4 frames-per-second (fps) 3D NLOS video recovery (128 × 128 × 512) in post-processing. Our method leverages the temporal similarity among adjacent frames and incorporates sparse priors and frequency filtering. This enables higher-quality reconstructions for complex scenes. Extensive experiments are conducted to verify the superior performance of our proposed algorithm both through simulations and real data.

Abstract Non‐line‐of‐sight (NLOS) imaging can reconstruct hidden objects by analyzing diffuse reflection of relay surfaces, and is potentially used in autonomous driving, medical imaging and national defense. Despite the challenges of low signal‐to‐noise ratio (SNR) and ill‐conditioned problem, NLOS imaging has developed rapidly in recent years. While deep neural networks have achieved impressive success in NLOS imaging, most of them lack flexibility when dealing with multiple spatial‐temporal resolution and multi‐scene images in practical applications. To bridge the gap between learning methods and physical priors, we present a novel end‐to‐end Multi‐scale Iterative Model‐guided Unfolding (MIMU), with superior performance and strong flexibility. Furthermore, we overcome the lack of real training data with a general architecture that can be trained in simulation. Unlike existing encoder‐decoder architectures and generative adversarial networks, the proposed method allows for only one trained model adaptive for various dimensions, such as various sampling time resolution, various spatial resolution and multiple channels for colorful scenes. Simulation and real‐data experiments verify that the proposed method achieves better reconstruction results both in quality and quantity than existing methods.

Single-photon avalanche diode (SPAD) has been widely used in active 3D imaging due to its extremely high photon sensitivity and picosecond time resolution. However, long-range active 3D imaging is still a great challenge, since only a few signal photons mixed with strong background noise can return from multiple reflectors of the scene due to the divergence of the light beam and the receiver's field of view (FoV), which would bring considerable distortion and blur to the recovered depth map. In this paper, we propose a deep learning based depth reconstruction method for long range single-photon 3D imaging where the “multiple-returns” issue exists. Specifically, we model this problem as a deblurring task and design a multi-scale convolutional neural network combined with elaborate loss functions, which promote the reconstruction of an accurate depth map with fine details and clear boundaries of objects. The proposed method achieves superior performance over several different sizes of receiver's FoV on a synthetic dataset compared with existing state-of-the-art methods and the trained model under a specific FoV has a strong generalization capability across different sizes of FoV, which is essential for practical applications. Moreover, we conduct outdoor experiments and demonstrate the effectiveness of our method in a real-world long range imaging system.