Joint Unsupervised Learning of Optical Flow and Egomotion with Bi-Level optimization
-
Altmetric Citations
Jiang, Shihao; Campbell, Dylan; Liu, Miaomiao; Gould, Stephen; Hartley, Richard
Description
We address the problem of joint optical flow and camera motion estimation in rigid scenes by incorporating geometric constraints into an unsupervised deep learning framework. Unlike existing approaches which rely on brightness constancy and local smoothness for optical flow estimation, we exploit the global relationship between optical flow and camera motion using epipolar geometry. In particular, we formulate the prediction of optical flow and camera motion as a bi-level optimization problem,...[Show more]
Collections | ANU Research Publications |
---|---|
Date published: | 2021 |
Type: | Conference paper |
URI: | http://hdl.handle.net/1885/311830 |
DOI: | 10.1109/3DV50981.2020.00078 |
Access Rights: | Open Access |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
Zac_3dv2020.pdf | 7.26 MB | Adobe PDF |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator