We invite paper contributions to discuss the current status and challenges of optical flow methods, applications of optical flow, evaluation metrics, and benchmarks that will help understand and shape the future of optical flow and its role in the field of computer vision. The workshop will focus on topics including (but not limited to):
Submissions will be in the form of short non-anonymous papers and will consist of a maximum of 14 pages (excluding references) in ECCV submission format. Paper length will not be taken into account in our review process. Note that most computer vision conferences have the policy that papers more than 4 pages (including references) will count as a full publication and cannot be resubmitted to another conference. So if you want to re-submit your paper to a future CVPR, the length of the camera ready should not exceed 4 pages including citations. Submissions must represent new work, i.e., work that has not been previously published or accepted for publication in a peer-reviewed venue. Accepted papers will be presented as posters, and the authors of the best paper will be invited to give an oral presentation. The workshop website will provide links to the accepted papers, and they will appear in a Springer Post-Proceedings series.
The best paper will receive an NVIDIA GPU, and we will raffle other smaller items among survey submissions.