2018/03/23 by Jia-Ren Chang, Chang, Jia-Ren, Yong‐Sheng Chen +2 · 81 citations
Computer Science · Mathematics · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Artificial intelligence #Benchmark (surveying) #Cartography #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Context (archaeology) #Convolutional neural network #Exploit #FOS: Computer and information sciences #Geography #Image Enhancement Techniques #Machine learning #Matching (statistics) #Mathematics #Pattern recognition (psychology) #Pooling #Pyramid (geometry) #Task (project management) #Volume (thermodynamics) #cs.CV
paper · pdf · doi:10.48550/arxiv.1803.08669
published in arXiv (Cornell University) (Cornell University) · CVPR 2018
arxiv created 2018/03/23 · openalex publication_date 2018/03/23 · arxiv updated 2018/03/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
Recent work has shown that depth estimation from a stereo pair of images can be formulated as a supervised learning task to be resolved with convolutional neural networks (CNNs). However, current architectures rely on patch-based Siamese networks, lacking the means to exploit context information for finding correspondence in illposed regions. To tackle this problem, we propose PSMNet, a pyramid stereo matching network consisting of two main modules: spatial pyramid pooling and 3D CNN. The spatial pyramid pooling module takes advantage of the capacity of global context information by aggregating context in different scales and locations to form a cost volume. The 3D CNN learns to regularize cost volume using stacked multiple hourglass networks in conjunction with intermediate supervision. The proposed approach was evaluated on several benchmark datasets. Our method ranked first in the KITTI 2012 and 2015 leaderboards before March 18, 2018. The codes of PSMNet are available at: https://github.com/JiaRenChang/PSMNet.