Get the latest tech news
CosAE: Learnable Fourier Series for Image Restoration
CosAE: Learnable Fourier Series for Image Restoration.
This method stands in contrast to a conventional Autoencoder that often sacrifices detail in their reduced-resolution bottleneck latent spaces. This encoding enables extreme spatial compression, e.g., 64x downsampled feature maps in the bottleneck, without losing detail upon decoding. Our method surpasses state-of-the-art approaches, highlighting its capability to learn a generalizable representation for image restoration.
Or read this on Hacker News