Pyramid Stereo Matching Network

TL;DR

The paper introduces PSMNet, a novel pyramid stereo matching network that effectively utilizes global context and 3D convolutional regularization to improve depth estimation from stereo images, achieving top results on benchmark datasets.

Contribution

The paper proposes PSMNet, combining spatial pyramid pooling and 3D CNNs with intermediate supervision for enhanced stereo matching accuracy.

Findings

Ranked first on KITTI 2012 and 2015 benchmarks.

Outperformed previous methods in depth estimation accuracy.

Effectively exploits global context for ill-posed regions.

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 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.