Journal
APPLIED SCIENCES-BASEL
Volume 12, Issue 4, Pages -Publisher
MDPI
DOI: 10.3390/app12042086
Keywords
stereo matching; deep learning; convolutional neural network; KITTI2015; KITTI2012
Categories
Funding
- Shandong Natural Science Foundation [ZR2021MF114]
- National Natural Science Foundation of China [61871342]
Ask authors/readers for more resources
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.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available