Image Matching: Local Features & Beyond
CVPR 2024 Workshop
We are happy to announce that the Sixth Workshop on Image Matching: Local Features and Beyond will be held at CVPR 2024 on June 17, 2024, in the afternoon, in Seattle, USA. The workshop will once again feature an open challenge on Kaggle. If you wish to receive announcements, please join our mailing list (expect 2-3 emails a year).
Schedule
RECORDING
- 13:00 - 13:15: Welcome (organizers)
- 13:15 - 14:00: Invited talk by Prof. Noah Snavely, (Google/Cornell): Title TBD
- 14:00 - 14:45: Invited talk by Prof. Juan Tardós (Universidad de Zaragoza): Visual SLAM inside the human body
- 14:45 - 15:00: Invited talk by Vincent Leroy (NAVER Labs): Dust3r - Geometric 3D vision made easy
- 15:00 - 15:15: Coffee break
- 15:15 - 16:05: Paper talks
- 15:15 - 15:25: DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector (Johan Edstedt, Georg Bökman, Zhenjun Zhao)
- 15:25 - 15:35: Affine-based Deformable Attention and Selective Fusion for Semi-dense Matching (Hongkai Chen, Zixin Luo, Yurun Tian, Xuyang Bai, Ziyu Wang, Lei Zhou, Zhen Mingmin, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan)
- 15:35 - 15:45: EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut Photography (Gabriele Berton, Gabriele Goletto, Gabriele Trivigno, Alex Stoken, Barbara Caputo, Carlo Masone)
- 15:45 - 15:55: XoFTR: Cross-modal Feature Matching Transformer (Önder Tuzcuoğlu, Aybora Koksal, Buğra Sofu, Sinan Kalkan, Aydin Alatan)
- 15:55 - 16:05: Are Deep Learning Models Pre-trained on RGB Data Good Enough for RGB-Thermal Image Retrieval? (Amulya Pendota, Sumohana Channappayya)
- 16:05 - 16:20: Coffee break
- 16:20 - 16:35: The 2024 Kaggle Image Matching Challenge
- 16:35 - 17:17: Challenge talks
- Speakers and number of talks TBA
- 17:17 - 17:30: Closing
News
- 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. Submissions must contain novel work and will be indexed in IEEE Xplore/CVF. They will receive at least two double-blind reviews.
Invited speakers
Organisers
Fabio
Bellavia
University of Palermo
Jiri
Matas
Czech Technical University
Dmytro
Mishkin
Czech Technical University, HOVER Inc.
Luca
Morelli
University of Trento, Bruno Kessler Foundation
Fabio
Remondino
Bruno Kessler Foundation
Weiwei
Sun
University of British Columbia
Amy
Tabb
USDA-ARS-AFRS
Eduard
Trulls
Google
Kwang Moo
Yi
University of British Columbia
Important dates
Update on March 12: we pushed the paper submission deadline by one week to give authors more time to submit.
- Paper submission deadline:
March 18, 2024 March 25, 2024.
- Paper reviews assigned on:
March 19, 2024 March 26, 2024.
- Paper reviews due on:
April 2, 2024 April 9, 2024.
- Notification to authors:
April 8, 2024 April 11, 2024.
- Camera-ready deadline:
April 11, 2024 April 12, 2024 (hard deadline on April 14).
- Challenge submission deadline: June 3, 2024 (please refer to the Kaggle website for the exact timeline).
- Workshop date: June 17, 2024, 1PM, Pacific Time.
We welcome PC self-nominations. If you’re willing to review for the workshop, please reach out to us at image-matching@googlegroups.com.
(All dates are at 11:59PM, Pacific Time, unless stated otherwise.)
Links
-
Previous websites: 2019, 2020, 2021, 2022, 2023.
-
Previous livestreams: 2020, 2021, 2023, 2024.
-
2019-2021 Image Matching Benchmark (used in previous editions of the challenge).
-
Previous challenges: 2020, 2021, 2022, 2023.
Please reach us with any questions at image-matching@googlegroups.com.