PUBLISHED ON OCT 2, 2016

Important information

Schedule

All times are MT (Mountain Time). For convenience, 9AM MT corresponds to 8AM PT, 11AM ET, 5PM CET, and 11PM in China.

  • 09:00-09:15: Welcome (full workshop slides)
  • 09:15-10:00: Invited talk by Prof. Davide Scaramuzza (University of Zurich/ETH Zurich)
  • 10:00-10:45: Invited talk by Prof. Marc Pollefeys (ETH Zurich/Microsoft)
  • 10:45-11:00: Workshop paper talk by Daniel Koguciuk: “Perceptual Loss for Robust Unsupervised Homography Estimation” (paper | recording)
  • 11:00-11:15: Workshop paper talk by Ufuk Efe: “DFM: A Performance Baseline for Deep Feature Matching” (paper | recording)
  • 11:15-11:45: Challenge presentation (organizers)
  • 11:45-12:15: Open discussion (organizers and participants)
  • 12:15-13:35: Invited challenge talks (8 x 10 minutes — speakers/schedule to be confirmed soon)
    • 12:15-12:25: Fabio Bellavia (University of Palermo)
    • 12:25-12:35: Prune Truong (ETH Zurich)
    • 12:35-12:45: Jiaming Sun/Xingyi He (Zhejiang University/SenseTime Research)
    • 12:45-12:55: Wei Jiang (University of British Columbia)
    • 12:55-13:05: Megvii Inc. Research 3D
    • 13:05-13:15: Youtu Lab, Tencent/Institute of Artificial Intelligence, Xiamen University (recording)
  • 13:15-13:20: Conclusion

About

Traditional, keypoint-based formulations for image matching are still very competitive on tasks such as Structure from Motion (SfM), despite recent efforts on tackling pose estimation with dense networks. In practice, many state-of-the-art pipelines still rely on methods that stood the test of time, such as SIFT or RANSAC.

In this workshop, we aim to encourage 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.

The 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 re-localization, such as privacy-preserving representations.

Organisers

Vassileios
Balntas Facebook
Vincent
Lepetit ENPC ParisTech
Jiri
Matas Czech Technical University
Dmytro
Mishkin Czech Technical University
Johannes
Schönberger Microsoft
Eduard
Trulls Google
Kwang Moo
Yi University of British Columbia

CVPR will be held at CVPR 2021, which will follow a virtual format once again, between June 19-25, 2021. The exact date of the workshop will be announced after the schedule is finalized. Keynote speakers will also be confirmed then. The workshop will once again feature an open challenge which will be announced in the following weeks.

The livestream for last year’s workshop remains available on YouTube.

Talks

News

  • June 28: The conference is over! Thanks for your participation, and hope to see you next year. Slides have been uploaded here.
  • June 21: Announcing the IMC challenge winners, and tentative schedule (top of this page). See you this Friday!
  • March 11: Announcing our invited speakers: Professors Marc Pollefeys and Davide Scaramuzza.
  • March 3: Announcing our call for papers. The challenge will be open in about ~1mo.
  • January 29: Updating website to announce the third (2021) edition of the workshop. Details on the workshop, challenge, and call for papers to follow soon.

Important dates

  • Paper submission deadline: April 9, 2021.
  • Notification to authors: April 16, 2021.
  • Camera-ready deadline: April 18, 2021 (hard deadline on April 20).
  • Challenge submission deadline: TBA (see challenge website)
  • Deadline for short descriptions on challenge submissions: TBA (see challenge website)
  • Workshop date: June 25, 2021, morning (exact schedule TBA)

(All dates are at 11:59PM, Pacific Time.)

Challenge

Contact

Please reach us with any questions at image-matching@googlegroups.com.




< prev | | next >

home