Pyramid Stereo Matching Network

Jia Ren Chang, Yong-Sheng Chen

研究成果: Conference contribution同行評審

814 引文 斯高帕斯(Scopus)

摘要

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: Rpatial 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.

原文English
主出版物標題Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
發行者IEEE Computer Society
頁面5410-5418
頁數9
ISBN(電子)9781538664209
DOIs
出版狀態Published - 14 12月 2018
事件31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 - Salt Lake City, United States
持續時間: 18 6月 201822 6月 2018

出版系列

名字Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN(列印)1063-6919

Conference

Conference31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
國家/地區United States
城市Salt Lake City
期間18/06/1822/06/18

指紋

深入研究「Pyramid Stereo Matching Network」主題。共同形成了獨特的指紋。

引用此