Moreover, the proposed method delivers impressive robustness at an extremely low scanning grid (i.e., 8

Active confocal non-line-of-sight (NLOS) imaging has successfully enabled seeing around corners relying on high-quality transient measurements. However, acquiring spatial-dense transient measurement is time-consuming, raising the question of how to reconstruct satisfactory results from under-scanning measurements (USM). The existing solutions, involving the traditional algorithms, however, are hindered by unsatisfactory results or long computing times. To this end, we propose the first deep-learning-based approach to NLOS imaging from USM. Our proposed end-to-end network is composed of two main components: the transient recovery network (TRN) and the volume reconstruction network (VRN). Specifically, TRN takes the under-scanning measurements as input, utilizes a multiple kernel feature extraction module and a multiple feature fusion module, and outputs sufficient-scanning measurements at the high-spatial resolution.

Our method capitalizes on neighbouring transient frames to aggregate the target 3D hidden volume.

In Figure 1, we present the results obtained with a total acquisition time of 25.6s and 102.4s, respectively. Furthermore, it is noteworthy that our paper introduces a universally applicable technique for NLOS imaging utilizing under-scanning measurements. The emitted pulses pass through a two-axis raster-scanning galvo mirror, transmitting onto the visible wall. The qualitative results are shown in Figure 1. To further validate the generalization capability of our model, we conduct tests on additional real-world data captured by our NLOS imaging system.

Moreover, the proposed method delivers impressive robustness at an extremely low scanning grid (i.e., 8

Active confocal non-line-of-sight (NLOS) imaging has successfully enabled seeing around corners relying on high-quality transient measurements. However, acquiring spatial-dense transient measurement is time-consuming, raising the question of how to reconstruct satisfactory results from under-scanning measurements (USM). The existing solutions, involving the traditional algorithms, however, are hindered by unsatisfactory results or long computing times. To this end, we propose the first deep-learning-based approach to NLOS imaging from USM. Our proposed end-to-end network is composed of two main components: the transient recovery network (TRN) and the volume reconstruction network (VRN). Specifically, TRN takes the under-scanning measurements as input, utilizes a multiple kernel feature extraction module and a multiple feature fusion module, and outputs sufficient-scanning measurements at the high-spatial resolution.