Seventh Workshop on Image Matching: Local Features & Beyond (original) (raw)

Image Matching: Local Features & Beyond

CVPR 2025 Workshop

We are happy to announce that the Seventh Workshop on Image Matching: Local Features and Beyond will be held at CVPR 2025 on June 11-12, 2025, in Nashville TN, USA. The workshop will once again feature an open challenge on Kaggle which will be announced soon. If you wish to receive announcements, please join our mailing list (expect 2-3 emails a year).

News

April 2, 2025: The Kaggle Image Matching Challenge 2025 is online.
March 8, 2025: Extending the paper submission deadline to March 17. Kaggle challenge will be announced soon.
January 10, 2025: Announcing the new edition of the workshop.
September 17, 2024: Publishing the recording for this year’s workshop
June 4, 2024: Announcing the schedule. The challenge concluded today!
March 25, 2024: The challenge is up!
March 12, 2024: Moved the paper submission deadline by one week, to give authors more time. News on the challenge soon!
January 15, 2024: Announcing the 2024 edition.

About

Matching two or more images across wide baselines is a core computer vision problem, with applications to stereo, 3D reconstruction, re-localization, SLAM, and retrieval, among many others. Until recently one of the last bastions of traditional handcrafted methods, they too have begun to be replaced with learned alternatives. Interestingly, these new solutions still rely heavily on design intuitions behind handcrafted methods. In short, we are clearly in a transition stage, and our workshop, held every year at CVPR since 2019, aims to address this, bringing together researchers across academia and industry to assess the true state of the field. We aim to establish what works, what doesn’t, what’s missing, and which research directions are most promising, while focusing on experimental validation.

Towards this end, every workshop edition has included an open challenge on local feature matching. Its results support our statement, as solutions have evolved from carefully tuned traditional baselines (e.g. SIFT keypoints with learned patch descriptors) to more modern solutions (e.g. transformers). Local features might have an expiration date, but true end-to-end solutions still seem far away. More importantly, the results of the Image Matching Challenges have shown that comprehensive benchmarking with downstream metrics is crucial to figure out how novel techniques compare with their traditional counterparts. Our ultimate goal is to understand the performance of algorithms in real-world scenarios, their failure modes, and how to address them, and to find out problems that emerge in practical settings but are sometimes ignored by academia. We believe that this effort provides a valuable feedback loop to the community.

Topics include (but are not limited to):

Formulations of keypoint extraction and matching pipelines with deep networks.
Application of geometric constraints into the training of deep networks.
Leveraging additional cues such as semantics and mono-depth estimates.
Methods addressing adversarial conditions where current methods fail (weather changes, day versus night, etc.).
Attention mechanisms to match salient image regions.
Integration of differentiable components into 3D reconstruction frameworks.
Connecting local descriptors/image matching with global descriptors/image retrieval.
Matching across different data modalities such as aerial versus ground.
Large-scale evaluation of classical and modern methods for image matching, by means of our open challenge.
New perception devices such as event-based cameras.
Other topics related to image matching, structure from motion, mapping, and re-localization, such as privacy-preserving representations.

Call for Papers

We invite paper submissions up to 8 pages, excluding references and acknowledgements. They should use the CVPR template (reviews are double-blind, so please hide author data in the pdf) and be submitted to the CMT site: