Learning Dense Wide Baseline Stereo Matching for People
Authors:
- 1 October 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2158-2167
Abstract
Existing methods for stereo work on narrow baseline image pairs giving limited performance between wide baseline views. This paper proposes a framework to learn and estimate dense stereo for people from wide baseline image pairs. A synthetic people stereo patch dataset (S2P2) is introduced to learn wide baseline dense stereo matching for people. The proposed framework not only learns human specific features from synthetic data but also exploits pooling layer and data augmentation to adapt to real data. The network learns from the human specific stereo patches from the proposed dataset for wide-baseline stereo estimation. In addition to patch match learning, a stereo constraint is introduced in the framework to solve wide baseline stereo reconstruction of humans. Quantitative and qualitative performance evaluation against state-of-the-art methods of proposed method demonstrates improved wide baseline stereo reconstruction on challenging datasets. We show that it is possible to learn stereo matching from synthetic people dataset and improve performance on real datasets for stereo reconstruction of people from narrow and wide baseline stereo data.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Large-Scale Data for Multiple-View StereopsisInternational Journal of Computer Vision, 2016
- General Dynamic Scene Reconstruction from Multiple View Video2015
- SMPLACM Transactions on Graphics, 2015
- Object scene flow for autonomous vehicles2015
- Learning to compare image patches via convolutional neural networks2015
- A Quantitative Evaluation of Confidence Measures for Stereo VisionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline StereoIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Stereo Processing by Semiglobal Matching and Mutual InformationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Surface Capture for Performance-Based AnimationIEEE Computer Graphics and Applications, 2007
- A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence AlgorithmsInternational Journal of Computer Vision, 2002