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.
Keywords
Pyramid (geometry)PoolingComputer scienceContext (archaeology)Artificial intelligenceBenchmark (surveying)Convolutional neural networkMatching (statistics)ExploitTask (project management)Pattern recognition (psychology)Computer visionMachine learningMathematics
Affiliated Institutions
Related Publications
Pyramid Scene Parsing Network
Scene parsing is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of global context information by different-region-base...
Feature Pyramid Networks for Object Detection
Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But pyramid representations have been avoided in recent object detectors...
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224 × 224) input image. This requirement is "artificial" and may reduce the recognition accuracy f...
DenseASPP for Semantic Segmentation in Street Scenes
Semantic image segmentation is a basic street scene understanding task in autonomous driving, where each pixel in a high resolution image is categorized into a set of semantic l...
HybridSN: Exploring 3-D–2-D CNN Feature Hierarchy for Hyperspectral Image Classification
Hyperspectral image (HSI) classification is widely used for the analysis of\nremotely sensed images. Hyperspectral imagery includes varying bands of images.\nConvolutional Neura...
Publication Info
- Year
- 2018
- Type
- preprint
- Pages
- 5410-5418
- Citations
- 1686
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
1686
OpenAlex
424
Influential
1401
CrossRef
Cite This
Jia-Ren Chang,
Yong‐Sheng Chen
(2018).
Pyramid Stereo Matching Network.
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
, 5410-5418.
https://doi.org/10.1109/cvpr.2018.00567
Identifiers
- DOI
- 10.1109/cvpr.2018.00567
- arXiv
- 1803.08669