Look Wider to Match Image Patches with Convolutional Neural Networks

Abstract

When a human matches two images, the viewer has a natural tendency to view the wide area around the target pixel to obtain clues of right correspondence. However, designing a matching cost function that works on a large window in the same way is difficult. The cost function is typically not intelligent enough to discard the information irrelevant to the target pixel, resulting in undesirable artifacts. In this paper, we propose a novel learn a stereo matching cost with a large-sized window. Unlike conventional pooling layers with strides, the proposed per-pixel pyramid-pooling layer can cover a large area without a loss of resolution and detail. Therefore, the learned matching cost function can successfully utilize the information from a large area without introducing the fattening effect. The proposed method is robust despite the presence of weak textures, depth discontinuity, illumination, and exposure difference. The proposed method achieves near-peak performance on the Middlebury benchmark.

arXiv commentpublished in SPL

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches
• Object Detectors Emerge in Deep Scene CNNs
• FlowNet: Learning Optical Flow with Convolutional Networks
• Learning the Matching Function

Cited by in corpus (11)

• Deep learning in remote sensing: a review
• A Survey on Deep Learning Techniques for Stereo-based Depth Estimation
• Pooling Methods in Deep Neural Networks, a Review
• FoodNet: Recognizing Foods Using Ensemble of Deep Networks
• Learning for Disparity Estimation through Feature Constancy
• A Survey on Deep Learning Architectures for Image-based Depth Reconstruction
• A Learning-based Framework for Hybrid Depth-from-Defocus and Stereo Matching
• Parallax Attention for Unsupervised Stereo Correspondence Learning
• Deep Eyes: Binocular Depth-from-Focus on Focal Stack Pairs
• Distilling Stereo Networks for Performant and Efficient Leaner Networks
• On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: a Survey