KevinJiang

The interesting fact is that after applying truncation trick, the result becomes much more better. (The left one is generated w/o truncation trick, namely setting `truncation_psi` to be 1, while...

Hi FebOne1, There are still problems with my implementation waiting to be solved. I think it is still a bit premature, thus I propose issue here for suggestions. I will...

Currently, the fid score of FFHQ@512 is 9.75, which is still higher than the official one.

Hi FebOne1, Actually, I do not follow the schema of estimating poses stated in the paper. I use FLAME and DECA to fit head model, and retrieve its pitch, yaw...

Hi shoutOutYangJie, Can you share your decoder architecture? I am really curious about it, since the original paper states that they use SoftMax activation. However, after many experiments, I failed,...

> > Hi, > > After days of training and debugging, my reimplementation has reached following results (currently training on ~15M images): > > sample0_128.mp4 > > sample0_512.mp4 > >...

> @RaymondJiangkw Could you release your implmentation codes ? Hi, Thanks for your attention! I promised that I will release my reimplementation and I will definitely do. I am currently...

Hi, I wonder whether you use the softmax activation as described in the paper? If so, can you provide with more details about the architecture of decoder? Besides, the reason...

> > Hi, > > I wonder whether you use the softmax activation as described in the paper? If so, can you provide with more details about the architecture of...

> > > Can I use 68 landmarks instead of 5 landmarks？ > > > > > > I think yes. In load_img.py insert your own landmarks loading with correct...