Chieh Hubert Lin

Thanks for the reply! Yes but no, in most cases, the flicking happens on the edges of the window, but in some cases, it happens in the view. However, as...

Thanks for the comments! Now I understand the intuitions! However, regarding the subsampling part, the SwappingAutoencoder uses strided convolution to reduce the spatial dimension in the encoder. Consider it is...

1. Oh, yes, it is a mistake, I never really read that values LoL 2. Which configuration are you using? And what are your pytorch and cuda versions? I sometimes...

That's weird. Could you run it a second or third time and see if that repeatedly happens? And you may disable the diveristy_z_loss in the .yaml config to see if...

The coords are only used in the structure synthesizer. In the paper Figure 3, if you use other types of padding, the generator learns to rely on that positional information,...

Yes, you are mostly correct. > does all patches also have the same local latent vector Zl? Remind that Z_local is of shape [B, C, H, W] (which has the...

We didn't benchmark that, but it is expected that InfinityGAN training will be slower than StyleGAN2, since (i) we have an additional structure synthesizer, and (ii) the padding-free generator requires...

Hi, sorry for the late reply. The released config was wrong (I don't know how the config get overwritten). Please use the updated config at `./configs/test/outpaint_with_fused_gen_256x256.yaml` and replace the flag...

Thanks for reporting, it should be `args.config`, I'll update the codes later. Meanwhile, it is recommended to set `LMDB_ROOTS` in `env_config.py`.

You can directly go for training if you download our lmdb file. The `prepare_data.py` was meant to build lmdb from an image folder, which is useful when you want to...