Pyramid Stereo Matching Network

CVPR 2018  ·  Jia-Ren Chang, Yong-Sheng Chen ·

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:

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Stereo-LiDAR Fusion KITTI Depth Completion Validation PSMNet RMSE 884 # 7