felix-ky
felix-ky
Hi, may I know how you compute the foreground color, Fig.2(c) in the paper ![image](https://github.com/foamliu/Deep-Image-Matting/assets/52780840/fbaab82d-b5c1-4d7f-87cf-e8fb226b96bb) and I found that the training images are not original images but foreground color for...
Hi, may I know how you compute the foreground color, Fig.2(c) in the paper ![image](https://github.com/foamliu/Deep-Image-Matting-PyTorch/assets/52780840/82936cbb-9547-44ae-9335-76cacb6ef01b) and I found that the training images are not original images but foreground color for...
I tried to train MDM unconditionally using amass instead of humanact12, but the num of joints in amass is 21 while humanact has 23.
Hi, great to see this fantastic project! However, i have not seen the training code in the repo, could you please offer the training code?
Hi, thnaks for releasing the great repo and paper. I evaluate matteformer and vitmatte (both using pretrained weight) on P3M500, but both model's MSE error (times 1e3, computed on unknown...