Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence

檔案

本條目沒有附加檔案。

至出版者網站查看(DOI) ›

日期

2019-01-01

期刊名稱

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)

卷期與頁次

頁 1890–1899

ISSN

1063-6919

ISBN

978-1-7281-3293-8

語言

英文

摘要

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.

所屬典藏

會議論文
顯示完整詮釋資料 統計資料

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

BibTeX RIS

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