Workshop: https://image-matching-workshop.github.io
CMT website for paper submission: https://cmt3.research.microsoft.com/IMW2025


___*Overview* ___

We're happy to announce the seventh (!) edition of the Image Matching Workshop, co-located as every year with CVPR 2025. Our goal 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 and pose estimation.


___*Challenge* ___

The workshop will once again feature an open challenge on Kaggle. In addition to complex scenarios with temporal changes, this year we added a further challenge: each dataset contains multiple scenes and distractor images, and you need to figure out what belongs together in addition to solving the 3D reconstruction problem.

The challenge final deadline is June 2, 2025. The total amount of the prize is $50K, see https://www.kaggle.com/competitions/image-matching-challenge-2025 for more informations.


___*Topics* ___

Workshop 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 relocalization, such as privacy-preserving representations.


___*Invited speakers* ___

- Johannes Schoenberger, Meta
- Jonáš Kulhánek, CTU Prague


___*Paper submission* ___

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 (linked above). Submissions must contain novel work and will be indexed in IEEE Xplore/CVF. They will receive at least two double-blind reviews.

We welcome PC self-nominations. If you’re willing to review for the workshop, please reach out at image-matching@googlegroups.com.


___*Important dates* ___

- Paper submission deadline: March 17, 2025
- Notification to authors: April 2, 2025
- Camera-ready deadline: April 4, 2025 (hard deadline on April 7)
- Workshop date: TBC (June 11 or 12, 2025)


___*Organizers* ___

- Fabio Bellavia, University of Palermo
- Jiri Matas, Czech Technical University in Prague
- Dmytro Mishkin, Czech Technical University in Prague/HOVER Inc.
- Luca Morelli, University of Trento/Bruno Kessler Foundation
- Fabio Remondino, Bruno Kessler Foundation
- Amy Tabb, USDA-ARS-AFRS
- Eduard Trulls, Google
- Kwang Moo Yi, University of British Columbia