DeepAI AI Chat
Log In Sign Up

Widening siamese architectures for stereo matching

by   Patrick Brandao, et al.

Computational stereo is one of the classical problems in computer vision. Numerous algorithms and solutions have been reported in recent years focusing on developing methods for computing similarity, aggregating it to obtain spatial support and finally optimizing an energy function to find the final disparity. In this paper, we focus on the feature extraction component of stereo matching architecture and we show standard CNNs operation can be used to improve the quality of the features used to find point correspondences. Furthermore, we propose a simple space aggregation that hugely simplifies the correlation learning problem. Our results on benchmark data are compelling and show promising potential even without refining the solution.


page 2

page 4

page 5

page 6


Comparison of Stereo Matching Algorithms for the Development of Disparity Map

Stereo Matching is one of the classical problems in computer vision for ...

FPGA-based Binocular Image Feature Extraction and Matching System

Image feature extraction and matching is a fundamental but computation i...

Fast Hierarchical Depth Map Computation from Stereo

Disparity by Block Matching stereo is usually used in applications with ...

Long Range Stereo Matching by Learning Depth and Disparity

Stereo matching generally involves computation of pixel correspondences ...

Cascaded multi-scale and multi-dimension convolutional neural network for stereo matching

Convolutional neural networks(CNN) have been shown to perform better tha...

Stereo Matching by Joint Energy Minimization

In [18], Mozerov et al. propose to perform stereo matching as a two-step...