Skip to content

(Anisotropic) Fourier Feature Positional Encodings #8564

Closed

Description

@NabJa

I would like to contribute specialized positional encodings. This issue is meant to track the request and gather feedback from the community and maintainers before I open a pull request with the implementation.

Is your feature request related to a problem? Please describe.
Sinusoidal and Learned positional encodings (PEs) are often suboptimal for medical images. This is especially the case for anistropic images and for videos (see pre-print accepted in ShapeMI@MICCAI here).

Describe the solution you'd like
I would like to add the positional encodings, described in the pre-print:

  1. Isotropic Fourier Feature Positional Encodings (IFPE)
  2. Anistropic Fourier Feature Positional Encodings (AFPE)

They could be implemented in a single function and used in the PatchEmbeddingBlock.

Describe alternatives you've considered
Alternatively the PEs would have to be imported from another library.

Activity

  1. added a commit that references this issue on Oct 31, 2025
    42a9947
  2. added 2 commits that reference this issue on Oct 31, 2025
    76c4391
    30e8263
  3. added a commit that references this issue on Jan 6, 2026
    30c85d9
  4. added a commit that references this issue on Feb 25, 2026
    0175ec5
  5. added a commit that references this issue on May 25, 2026
    9b52b9c
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions