Non-fusion time-resolved depth image reconstruction using a highly efficient neural network architecture

Single-photon avalanche diodes (SPAD) are powerful sensors for 3D light detection and ranging (LiDAR) in low scenarios due to their single-photon sensitivity. However, accurately retrieving information from noisy time-of-arrival (ToA) point clouds remains a challenge. This paper proposes photon-efficient, non-fusion neural network architecture that can directly reconstruct high-fidelity depth images ToA data without relying on other guiding images. Besides, the was compressed via low-bit quantization scheme so it is suitable be implemented embedded hardware platforms. The proposed quantized achieves superior reconstruction accuracy fewer parameters than previously reported networks.