Bo Liu

ablation experiments for latent-replacing pretraining strategy

1

I don't see the ablation experiments in the paper “Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Models” about the latent-replacing pretraining strategy and I would like to know...

About LOLv2_real configuration

6

Hello, we use the config file in the folder 'options/train/LOLv2_real.yml' to retrain the model, but the results obtained are a little worse than the ones presented in the paper. I...

About inference image sizes

1

Hi, I have a problem when i use the Frequency Stage in your network architecture: I train the model with 256x256 image patches, but i get some strange results when...

To my confusion, I see "quantize" in the list. As far as I know, Autoencoder contains "encoder, decoder, quant_conv,post_quant_conv" part. Did you write quant_conv wrong or just quantize is meaningless?