Non-destructive three-dimensional measurement of hand vein based on self-supervised network

TL;DR

This paper introduces SDMNet, a self-supervised neural network for 3D hand vein measurement that does not require disparity labels, achieving high accuracy on multiple datasets and outperforming supervised methods.

Contribution

The paper presents a novel self-supervised stereo matching network that accurately estimates disparity maps without labeled data, specifically applied to hand vein 3D measurement.

Findings

SDMNet outperforms state-of-the-art supervised methods on multiple datasets.

The method effectively estimates dense disparity maps without disparity labels.

High-quality 3D hand vein measurements achieved using self-supervised learning.

Abstract

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.