Underwater 3-D Point Cloud Reconstruction of a Single Sonar Image Based on Pseudo Front View

This article aims to present a novel method for underwater 3-D point cloud reconstruction by estimating the pseudo front view from a single sonar image. Since the pseudo front view contains elevation, azimuth, and depth information, it can be easily transformed into a point cloud using formulas that relate polar and Cartesian coordinate systems. To achieve this, we utilize the U-Net++ network as the baseline to generate the pseudo front view. To address the challenge of scale compression caused by using inverse depth as the ground truth during training process, we employ the scale-invariant logarithmic (SILog) loss as one of the loss functions. This approach helps generate better training outcomes by balancing the extreme values in the depth ground truth. Additionally, we introduce a novel sonar-specific loss function, the sonar weighted loss (SWL), designed to capture the unique characteristics of sonar image generation and to differentiate the training of sonar pseudo front view depth images from general depth image training. Finally, we conduct extensive experiments using both open-source datasets (i.e., water tank and floating object) and real-world scenarios to comprehensively evaluate the effectiveness of the proposed method. The experimental results demonstrate its robustness and accuracy in 3-D reconstruction tasks. On the water tank dataset, the proposed method achieves an 87.24% reduction in 3-D reconstruction error compared to A2FNET. On the floating object dataset, it further outperforms ElevateNet (a more advanced baseline than A2FNET), reducing the 3-D reconstruction error by 74.13%. These results highlight the effectiveness of the proposed method and its practical potential for underwater 3-D reconstruction using imaging sonars.