Haitian Zheng
Haitian Zheng
Hi, I noticed that for AdaptiveFeatureGenerator, the encoder is implemented using padding of Conv, `self.layer1 = norm_layer(nn.Conv2d(opt.spade_ic, ndf, kw, stride=1, padding=pw))` However, the warping images have strong artifacts at boundry....
I want to train CoCosNet for other datasets, however, I'm not sure how the similar reference image for ADE20K dataset (ade20k_ref.txt) is generated. Could you elaborate on it more? Thanks!
Thank you for sharing the pretrained models. In the current readme.me, it seems that the COCO-Stuff (labels to photos) checkpoint is linked to the Place2 inpainting checkpoints. Wonder if the...
First, thank you for the impressive work! Currently, I am re-implementing a pytorch version of co-mod-gan, and I have several questions regarding the model: 1. Have you tried different R1...
Thank you for the nice code. I wonder if you could explain how the CLIP-guided sampling works. Thank you!