The goal of this workshop is to encourage and highlight novel strategies for image matching that deviate from and advance traditional formulations, with a focus on large-scale, wide-baseline matching for 3D reconstruction or pose estimation. This can be achieved by applying new technologies to sparse feature matching, or doing away with keypoints and descriptors entirely.
Workshop topics include (but are not limited to):
In order to advance research in these areas, we have issued a public challenge which contains two new datasets. Winners will be awarded prizes. For details please refer to the website.
We invite paper submissions in two tracks:
Workshop papers must contain novel work. They will receive at least two reviews with a single-blind policy. Accepted papers will be indexed on CVF and presented as posters in the workshop.
Extended abstracts may contain work previously published or currently under review. They will be made publicly available as non-archival reports, allowing for future submissions, and can be submitted up to the challenge deadline. Extended abstracts are eligible for poster presentation, by invitation.
Both tracks are eligible for challenge prizes. Papers will be selected based on novelty, relevance to workshop topics, technical merit, and performance in the challenge, if applicable.
(All dates are 11:59PM in Pacific Time.)