00:00:00 / 00:00:00

Does visual experience give rise to geometry?

By Maks Ovsjanikov

Appears in collection : Geometry & Computing / Géométrie & Informatique

In this talk, I will discuss two recent projects that aim to analyze the relation between features learned by vision models from 2D observations and the geometry of the 3D world. In the first project we investigate whether vision features learned from the experiences of unique individuals share a common geometric structure and whether this structure enables solving downstream tasks. In the second project, we consider whether it is possible to learn the SE(3) group structure of Euclidean transformations purely from passive visual experience. Both of these projects shed light on whether machine learning models, trained purely through passive observation on massive amounts of data, can "understand" geometry, and whether there are limits to such training.

Information about the video

Citation data

  • DOI 10.24350/CIRM.V.20539303
  • Cite this video Ovsjanikov, Maks (06/10/2026). Does visual experience give rise to geometry?. CIRM. Audiovisual resource. DOI: 10.24350/CIRM.V.20539303
  • URL https://dx.doi.org/10.24350/CIRM.V.20539303

Domain(s)

Bibliography

  • HAN, Tengda, EBRAHIMI, Sayna, GOKAY, Dilara, et al. Unique lives, shared world: Learning from single-life videos. In : Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2026. p. 24021-24030.
  • CHEN, Caroline, EBRAHIMI, Sayna, KITASHOV, Fedor, et al. SeeSE3: Emergence of 3D Space in Vision Features. arXiv preprint arXiv:2607.14228, 2026. - https://doi.org/10.48550/arXiv.2607.14228

Last related questions on MathOverflow

You have to connect your Carmin.tv account with mathoverflow to add question

Ask a question on MathOverflow




Register

  • Bookmark videos
  • Add videos to see later &
    keep your browsing history
  • Comment with the scientific
    community
  • Get notification updates
    for your favorite subjects
Subscribe illustration
Give feedback