Robust photon-efficient imaging using a pixel-wise residual shrinkage network
This work addresses photon-efficient 3D imaging for applications like LiDAR in challenging scenarios, representing a strong specific gain in a domain-specific area.
The paper tackles the problem of precise depth image prediction from single-photon LiDAR data with limited photon counts and high noise by proposing a pixel-wise residual shrinkage network that adaptively generates optimal thresholds for each pixel and redefines the optimization target as pixel-wise classification. The model outperforms state-of-the-art methods and maintains robust performance under different signal-to-noise ratios, including an extreme case of 1:100.
Single-photon light detection and ranging (LiDAR) has been widely applied to 3D imaging in challenging scenarios. However, limited signal photon counts and high noises in the collected data have posed great challenges for predicting the depth image precisely. In this paper, we propose a pixel-wise residual shrinkage network for photon-efficient imaging from high-noise data, which adaptively generates the optimal thresholds for each pixel and denoises the intermediate features by soft thresholding. Besides, redefining the optimization target as pixel-wise classification provides a sharp advantage in producing confident and accurate depth estimation when compared with existing research. Comprehensive experiments conducted on both simulated and real-world datasets demonstrate that the proposed model outperforms the state-of-the-arts and maintains robust imaging performance under different signal-to-noise ratios including the extreme case of 1:100.