Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching #156

Open
yiskw713 opened this issue Jul 7, 2020 · 0 comments

Comments

@yiskw713
Copy link
Owner

yiskw713 commented Jul 7, 2020

INFO

author

Pengpeng Liu, Irwin King, Michael Lyu, Jia Xu

affiliation

conference or year

CVPR2020

link

arXiv
実装

概要

自己教師あり学習で,optical flow推定とstereo matching を学習する手法を提案.
本研究では,stereo matchingをoptical flow の特殊な場合と捉え,図のように4枚のステレオ画像から,12通りの幾何学的な一貫性の制約を用いて,自己教師あり学習を実現する.
さらに,新たな代理タスクを追加することによって,精度向上を測った.
KITTI 2012 and 2015で検証を行い,KITTI 2012においてはいくつかの教師あり学習の手法を上回る性能を残している
Screen Shot 2020-07-07 at 19 32 56

提案手法

検証

新規性

議論,展望

Comment

date

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant