Survey on unsupervised learning methods for optical flow estimation
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Optical flow is an important component in many computer vision applications. Thanks to deep learning, there have been great improvements in optical flow estimation in the past several years. But all of the top performing models are trained using a supervised method, on synthetic data sets. As the creation of accurately labeled optical flow data sets from real world images is incredibly difficult, many researchers have turned to developing unsupervised approaches. In this paper we conduct a survey of some of the most recent papers in unsupervised learning of optical flow, and present some of the key elements that are universally utilized. In addition, we did a results comparison, and found that the best performing unsupervised models are UnDAF-RAFT for the MPI-Sintel benchmark, and UpFlow on the KITTI benchmark. But both models still have considerably worse results when compared to supervised methods.
Original language | English |
---|---|
Title of host publication | ICTC 2022 - 13th International Conference on Information and Communication Technology Convergence : Accelerating Digital Transformation with ICT Innovation |
Number of pages | 4 |
Publisher | IEEE Computer Society Press |
Publication date | 2022 |
Pages | 591-594 |
ISBN (Electronic) | 9781665499392 |
DOIs | |
Publication status | Published - 2022 |
Event | 13th International Conference on Information and Communication Technology Convergence, ICTC 2022 - Jeju Island, Korea, Republic of Duration: 19 Oct 2022 → 21 Oct 2022 |
Conference
Conference | 13th International Conference on Information and Communication Technology Convergence, ICTC 2022 |
---|---|
Land | Korea, Republic of |
By | Jeju Island |
Periode | 19/10/2022 → 21/10/2022 |
Series | International Conference on ICT Convergence |
---|---|
Volume | 2022-October |
ISSN | 2162-1233 |
Bibliographical note
Publisher Copyright:
© 2022 IEEE.
- deep learning, occlusion, Optical flow, photometric consistency, self-supervision, smooth regularization, unsupervised learning
Research areas
ID: 344654316