Equivariant Vision: From Theory to Practice

CVPR 2025 Workshop, Nashville, TN
June 11-12 2025 (TBD), 08:30-17:00

Exploiting symmetry in structured data is a powerful way to improve the generalization ability, data efficiency, and robustness of AI systems, which leads to the research direction of equivariant deep learning. Showing its effectiveness, it has been widely adopted in a large variety of subareas of computer vision, from 2D image analysis to 3D perception, as well as further applications such as medical imaging and robotics.

Our topics include but are not limited to:

  • Theoretical foundations of equivariant deep learning with symmetry and group theory.
  • Equivariance by design: Neural network architectures and mathematical guarantees.
  • Equivariance from data: Learning equivariant and invariant features.
  • Applications in 2D and 3D computer vision and robotics.
  • Applications in broader science: computational biology, medicine, natural science, etc.
  • Equivariance in the large-model era and potential future directions.

Keynote Speakers
Maani Ghaffari
UMich
Tess Smidt
MIT
Vincent Sitzmann
MIT
Thomas Mitchel
PlayStation
Taco Cohen
Qualcomm
Gabriele Cesa
Qualcomm
Robin Walters
Northeastern
Tutorial
Chien Erh Lin
UMich
Tzu-Yuan Lin
UMich
Schedule
Morning Session 08:30-11:45
Opening Remarks and Welcome 08:30-08:45
Keynote Talk: Speaker TBD
Topic TBD
08:45-09:30
Keynote Talk: Speaker TBD
Topic TBD
09:30-10:15
Coffee Break 10:15-10:30
Keynote Talk: Speaker TBD
Topic TBD
10:30-11:15
Keynote Talk: Speaker TBD
Topic TBD
11:15-12:00
Lunch Break 12:00-13:30
Afternoon Session 13:30-17:00
Keynote Talk: Speaker TBD
Topic TBD
13:30-14:15
Keynote Talk: Speaker TBD
Topic TBD
14:15-15:00
Coffee Break 15:00-15:15
Keynote Talk: Speaker TBD
Topic TBD
15:15-16:00
Tutorial: Chien Erh Lin, Tzu-Yuan Lin
Topic TBD
16:00-16:45
Conclusion 16:45-17:00
Organizers
Congyue Deng
Stanford
Evangelos Chatzipantazis
UPenn
Jiahui Lei
UPenn
Yinshuang Xu
UPenn
Stefanos Pertigkiozoglou
UPenn
Minghan Zhu
UMich & UPenn
Huazhe Xu
Tsinghua
Thomas Mitchel
PlayStation
Leonidas Guibas
Stanford
Kostas Daniilidis
UPenn