|
| |||||||||||||||
IMW 2026 : CVPR Workshop on Image Matching: Local Features and Beyond 2026 | |||||||||||||||
| Link: https://image-matching-workshop.github.io | |||||||||||||||
| |||||||||||||||
Call For Papers | |||||||||||||||
|
Workshop: https://image-matching-workshop.github.io
CMT website for paper submission: https://cmt3.research.microsoft.com/IMW2026 *Overview* The 8th edition of the Image Matching Workshop is co-located as every year with CVPR 2026. 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 hosted on Kaggle. This year's challenge extends the previous year one with the purpose of serving as a reference dataset with a larger life span. Teams with best submissions will be invited to present their solutions at the workshop. Challenge website: https://www.kaggle.com/competitions/image-matching-challenge-2025-ongoing *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. - Large-scale evaluation of classical and modern methods for image matching, by means of our open challenge. - Matching across different data modalities such as aerial versus ground. - Leveraging additional cues such as semantics and mono-depth estimates. - Attention mechanisms to match salient image regions. - Connecting local descriptors/image matching with global descriptors/image retrieval. - Methods addressing adversarial conditions where current methods fail (weather changes, day versus night, etc.). - Integration of differentiable components into 3D reconstruction frameworks. - 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* - Paul-Edouard Sarlin, Google - Nikhil Keetha, CMU / Meta *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. *Important dates* - Paper submission deadline: March 16, 2026. - Notification to authors: April 6, 2026. - Camera-ready deadline: April 8, 2026 (hard deadline on April 11). - Workshop date: TBC (June 3 or 4, 2026). *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 |
|