HAT
HAT copied to clipboard
XPixelGroup
CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer Arxiv - HAT: Hybrid Attention Transformer for Image Restoration
How to use the pretrained model using python? I wonder if there is a script can increase a picture's resolution ? I'm afraid that chaiNNer will destory my python environment....
The model seems to be outputting images with many large pixel-like squares. These are clearly visible in the enlarged image. The original image is 700x500 image. 
I'd like to ask about your great work. Is it possible to run it on a grayscale dataset? If so what should I change? I changed a number of input...
Could you please provide config for Real_HAT_GAN_SRx4 checkpoint
2022-12-23 14:30:11,207 INFO: Use Exponential Moving Average with decay: 0.999 2022-12-23 14:30:20,212 INFO: Network [HAT] is created. 2022-12-23 14:30:20,331 INFO: Loss [L1Loss] is created. 2022-12-23 14:30:20,342 INFO: Model [HATModel] is...
Thank you for sharing an excellent work!! It seems only the GAN_SR_x4 model is released. Can you release the pretrained model and config for x2?
Thank you very much
Would it require modification of just the HAT package or also basicsr? Any rough idea of the required steps? Thanks!
what's the function of the file ‘hat_arch.py’?
Metadata
Owner
Metadata
CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer Arxiv - HAT: Hybrid Attention Transformer for Image Restoration