Adaptive Deconvolution-based stereo matching Net for Local Stereo Matching

TL;DR

This paper introduces ADSM net, an efficient deep learning model for local stereo matching that adaptively enlarges feature maps to improve accuracy without increasing computational complexity excessively.

Contribution

It proposes a novel CNN architecture with deconvolution layers to adaptively expand feature maps, balancing accuracy and efficiency in stereo matching.

Findings

Achieves competitive accuracy on KITTI datasets.

Reduces network parameters compared to existing methods.

Balances accuracy and computational complexity effectively.

Abstract

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 KITTI 2012 and 2015 datasets demonstrate that the proposed method can achieve a good trade-off between accuracy and complexity.