Adaptive Deconvolution-Based Stereo Matching Net for Local Stereo Matching

In deep learning-based local stereo matching methods, larger image patches usually bring better stereo matching accuracy. However, it is unrealistic to increase the size of the image patch size without restriction. Arbitrarily extending the patch size will change the local stereo matching method into the global stereo matching method, and the matching accuracy will be saturated. We simplified the existing Siamese convolutional network by reducing the number of network parameters and propose an efficient CNN based structure, namely adaptive deconvolution-based disparity matching net (ADSM net) by adding deconvolution layers to learn how to enlarge the size of input feature map for the following convolution layers. Experimental results on the KITTI2012 and 2015 datasets demonstrate that the proposed method can achieve a good trade-off between accuracy and complexity.

Automated summary

In deep learning-based local stereo matching, larger image patches improve accuracy, but unrestricted enlargement leads to saturation. This study proposes an adaptive deconvolution-based disparity matching network by simplifying Siamese convolutional network and adding deconvolution layers, achieving a good trade-off between accuracy and complexity.