Non-destructive three-dimensional measurement of hand vein based on self-supervised network
This addresses the challenge of inaccessible 3D labels in medical imaging for non-destructive hand vein measurement, though it is incremental as it adapts self-supervised techniques to a specific domain.
The paper tackles the problem of 3D hand vein measurement without requiring labeled disparity data by proposing a self-supervised network (SDMNet) for binocular disparity matching, achieving results that outperform state-of-the-art supervised methods on datasets including KITTI and vein datasets.
At present, supervised stereo methods based on deep neural network have achieved impressive results. However, in some scenarios, accurate three-dimensional labels are inaccessible for supervised training. In this paper, a self-supervised network is proposed for binocular disparity matching (SDMNet), which computes dense disparity maps from stereo image pairs without disparity labels: In the self-supervised training, we match the stereo images densely to approximate the disparity maps and use them to warp the left and right images to estimate the right and left images; we build the loss function between estimated images and original images for self-supervised training, which adopts perceptual loss to help improve the quality of disparity maps in both detail and structure. Then, we use SDMNet to obtain disparities of hand vein. SDMNet has achieved excellent results on KITTI 2012, KITTI 2015, simulated vein dataset and real vein dataset, outperforming many state-of-the-art supervised matching methods.