Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
1899 | en_US |
dc.citation.spage |
1890 | en_US |
dc.citation.woscount |
3 | en_US |
dc.contributor.author |
Lai, Hsueh-Ying | en_US |
dc.contributor.author |
Tsai, Yi-Hsuan | en_US |
dc.contributor.author |
Chiu, Wei-Chen | en_US |
dc.contributor.department |
交大名義發表 | zh_TW |
dc.contributor.department |
National Chiao Tung University | en_US |
dc.date.accessioned |
2020-10-05T02:00:29Z | |
dc.date.available |
2020-10-05T02:00:29Z | |
dc.date.issued |
2019-01-01 | en_US |
dc.description.abstract |
Stereo matching and flow estimation are two essential tasks for scene understanding, spatially in 3D and temporally in motion. Existing approaches have been focused on the unsupervised setting due to the limited resource to obtain the large-scale ground truth data. To construct a self-learnable objective, co-related tasks are often linked together to form a joint framework. However, the prior work usually utilizes independent networks for each task, thus not allowing to learn shared feature representations across models. In this paper, we propose a single and principled network to jointly learn spatiotemporal correspondence for stereo matching and flow estimation, with a newly designed geometric connection as the unsupervised signal for temporally adjacent stereo pairs. We show that our method performs favorably against several state-of-the-art baselines for both unsupervised depth and flow estimation on the KITTI benchmark dataset. | en_US |
dc.identifier.doi |
10.1109/CVPR.2019.00199 | en_US |
dc.identifier.isbn |
978-1-7281-3293-8 | en_US |
dc.identifier.issn |
1063-6919 | en_US |
dc.identifier.journal |
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) | en_US |
dc.identifier.uri |
http://dx.doi.org/10.1109/CVPR.2019.00199 | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/155012 | |
dc.identifier.wosnumber |
WOS:000529484002006 | en_US |
dc.language.iso |
en_US | en_US |
dc.title |
Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence | en_US |
dc.type |
Proceedings Paper | en_US |
檔案
本條目沒有附加檔案。
所屬典藏: 會議論文
引用此條目
Lai, H.-Y., Tsai, Y.-H., & Chiu, W.-C. (2019). Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 1890–1899. https://doi.org/10.1109/CVPR.2019.00199
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/155012