Abstract
Supervised deep networks are among the best methods for finding correspondences in stereo image pairs. Like all supervised approaches, these networks require ground truth data during training. However, collecting large quantities of accurate dense correspondence data is very challenging. We propose that it is unnecessary to have such a high reliance on ground truth depths or even corresponding stereo pairs. Inspired by recent progress in monocular depth estimation, we generate plausible disparity maps from single images. In turn, we use those flawed disparity maps in a carefully designed pipeline to generate stereo training pairs. Training in this manner makes it possible to convert any collection of single RGB images into stereo training data. This results in a significant reduction in human effort, with no need to collect real depths or to hand-design synthetic data. We can consequently train a stereo matching network from scratch on datasets like COCO, which were previously hard to exploit for stereo. Through extensive experiments we show that our approach outperforms stereo networks trained with standard synthetic datasets, when evaluated on KITTI, ETH3D, and Middlebury. Code to reproduce our results is available at https://github.com/nianticlabs/stereo-from-mono/.
Original language | English |
---|---|
Title of host publication | Computer Vision – ECCV 2020 |
Subtitle of host publication | 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part I |
Publisher | Springer |
Pages | 722-740 |
Number of pages | 19 |
ISBN (Electronic) | 978-3-030-58452-8 |
ISBN (Print) | 978-3-030-58451-1 |
DOIs | |
Publication status | Published - 3 Nov 2020 |
Event | 16th European Conference on Computer Vision - Virtual conference Duration: 23 Aug 2020 → 28 Aug 2020 https://eccv2020.eu/ |
Publication series
Name | Lecture Notes in Computer Science |
---|---|
Publisher | Springer, Cham |
Volume | 12346 |
ISSN (Print) | 0302-9743 |
ISSN (Electronic) | 1611-3349 |
Conference
Conference | 16th European Conference on Computer Vision |
---|---|
Abbreviated title | ECCV 2020 |
City | Virtual conference |
Period | 23/08/20 → 28/08/20 |
Internet address |
Keywords / Materials (for Non-textual outputs)
- Stereo matching
- Correspondence training data