When Fast Fourier Transform Meets Transformer for Image Restoration (2024)(github.com)
80 分 | 作者 teleforce 2天前
6 条评论
- jongala 16小时前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 13小时前I'd like to see a sequel where the fractional fourier transform is used for image restoration
- TimorousBestie 21小时前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 20小时前I do wonder if a wavelet transform might be better.
- TimorousBestie 18小时前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 20小时前See also: CosAE: Learnable Fourier Series for Image Restoration (2024)
- waynecochran 18小时前Was there a conclusion?
- gryfft 22小时前[2024]