emlcpfx
emlcpfx
> I think it can be solved by new face detection  Can you please elaborate? I'd love to implement this with EMOCA.
> @timlod Yes, everything is exactly as you wrote it. At first I thought that the face points are used directly to generate the model, but after more detailed analysis...
@yfeng95 Can you please weigh in on the technique that @mosvlad is proposing?
I found a hacky fix for how this eye alignment was affecting our work. Check it out here: https://github.com/radekd91/emoca/issues/61#issuecomment-1683007725 There are a lot of very smart people on this board,...
Did you find an answer to this, or get it to export an .obj animation?
@Griffin98 Where is that in the rendering code?
@littlePrince126 have you looked into the SPIGA repo for 2D landmarks? https://github.com/andresprados/SPIGA
https://github.com/yfeng95/DECA/issues/110
Were you able to train the model?
It works with my 3090 on Windows and WSL Ubuntu. Off the top of my head, you need to use a more recent version of PyTorch.