Title: Pyramid Stereo Matching Network
Authors: Chang, Jia-Ren
Chen, Yong-Sheng
資訊工程學系
Department of Computer Science
Issue Date: 1-Jan-2018
Abstract: 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 ill-posed 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.
URI: http://dx.doi.org/10.1109/CVPR.2018.00567
http://hdl.handle.net/11536/151019
ISSN: 1063-6919
DOI: 10.1109/CVPR.2018.00567
Journal: 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
Begin Page: 5410
End Page: 5418
Appears in Collections:Conferences Paper