Abstract
We present a novel method that predicts a confidence to improve the accuracy of an estimated depth map in stereo matching. In contrast to existing learning based approaches relying on hand-crafted confidence features, we cast this problem into a convolutional neural network, learned using both a matching cost volume and its associated disparity map. As the size of the matching cost volume varies depending on a search range of stereo image pairs, we propose to use a top-K matching probability volume layer so that an input size for convolutional layers remains unchanged. Experimental results demonstrate that the proposed method outperforms the state-of-the-art confidence estimation approaches on various benchmarks.
Original language | English |
---|---|
Title of host publication | 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings |
Publisher | IEEE Computer Society |
Pages | 992-996 |
Number of pages | 5 |
ISBN (Electronic) | 9781509021758 |
DOIs | |
State | Published - 2 Jul 2017 |
Event | 24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China Duration: 17 Sep 2017 → 20 Sep 2017 |
Publication series
Name | Proceedings - International Conference on Image Processing, ICIP |
---|---|
Volume | 2017-September |
ISSN (Print) | 1522-4880 |
Conference
Conference | 24th IEEE International Conference on Image Processing, ICIP 2017 |
---|---|
Country/Territory | China |
City | Beijing |
Period | 17/09/17 → 20/09/17 |
Bibliographical note
Publisher Copyright:© 2017 IEEE.
Keywords
- Confidence prediction
- Convolutional neural networks
- Depth refinement
- Matching probability
- Stereo matching