NHacker Next
  • new
  • past
  • show
  • ask
  • show
  • jobs
  • submit
When Fast Fourier Transform Meets Transformer for Image Restoration (2024) (github.com)
jongala 5 hours ago [-]
Relatedly, Marcin Wichary wrote a nice post about using FFT to remove moiré and halftone effects when scanning images that were printed with halftones.

It's from 2021: Moiré no More (https://newsletter.shifthappens.site/archive/moire-no-more/).

krackers 1 hours ago [-]
I'd like to see a sequel where the fractional fourier transform is used for image restoration
TimorousBestie 9 hours ago [-]
There have been some interesting advances in trying to add spectral information to the data that a learning architecture has at its disposal, but there are a couple roadblocks that I don’t think have been solved yet.

1. Complex-valued NNs are not an easy generalization of real ones.

2. A localization in one domain implies non-local behavior in the other (this is the Fourier uncertainty principle).

Fourier Neural Operators (FNOs) come close to what I want to see in this area but since they enforce sparsity in the spectral domain their application is necessarily limited.

FuckButtons 8 hours ago [-]
I do wonder if a wavelet transform might be better.
TimorousBestie 7 hours ago [-]
I think one can do better with a wavelet, shearlet, or curvelet transform that is adapted to the problem domain at hand. But the uncertainty principle still haunts those transforms, and anyway the goal is to be domain-agile.
sorenjan 8 hours ago [-]
See also: CosAE: Learnable Fourier Series for Image Restoration (2024)

https://sifeiliu.net/CosAE-page/

waynecochran 7 hours ago [-]
Was there a conclusion?
gryfft 10 hours ago [-]
[2024]
9 hours ago [-]
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact
Rendered at 23:40:23 GMT+0000 (Coordinated Universal Time) with Vercel.