Conference item
GA-Net: Guided aggregation net for end-to-end stereo matching
- Abstract:
- In the stereo matching task, matching cost aggregation is crucial in both traditional methods and deep neural network models in order to accurately estimate disparities. We propose two novel neural net layers, aimed at capturing local and the whole-image cost dependencies respectively. The first is a semi-global aggregation layer which is a differentiable approximation of the semi-global matching, the second is the local guided aggregation layer which follows a traditional cost filtering strategy to refine thin structures. These two layers can be used to replace the widely used 3D convolutional layer which is computationally costly and memory-consuming as it has cubic computational/memory complexity. In the experiments, we show that nets with a two-layer guided aggregation block easily outperform the state-of-the-art GC-Net which has nineteen 3D convolutional layers. We also train a deep guided aggregation network (GA-Net) which gets better accuracies than state-of-the-art methods on both Scene Flow dataset and KITTI benchmarks.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 9.4MB, Terms of use)
-
- Publisher copy:
- 10.1109/CVPR.2019.00027
Authors
- Publisher:
- IEEE
- Host title:
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Journal:
- Conference on Computer Vision and Pattern Recognition (CVPR 2019) More from this journal
- Pages:
- 185-194
- Publication date:
- 2020-01-09
- Acceptance date:
- 2019-03-06
- DOI:
- ISSN:
-
2575-7075
- ISBN:
- 9781728132938
- Keywords:
- Pubs id:
-
pubs:995255
- UUID:
-
uuid:ba85d4c7-adaa-4148-9d92-c5d413f609ed
- Local pid:
-
pubs:995255
- Source identifiers:
-
995255
- Deposit date:
-
2019-05-01
- ARK identifier:
Terms of use
- Copyright holder:
- IEEE
- Copyright date:
- 2020
- Notes:
- Copyright © 2019 IEEE. This is the accepted manuscript version of the article. The final version is available online from IEEE at: https://doi.org/10.1109/CVPR.2019.00027
If you are the owner of this record, you can report an update to it here: Report update to this record