A

Results 6 comments of A

The results on the NoW Challenge list calculated using test data? The results measured by the DECA validation set have a large error with the test set.

In the rigid alignment step, I found that gt scan and pred mesh failed to align, is there any solution? I measured that the mean of DECA on the validation...

Rendering

> change config decalib\utils\config.py > > cfg.model.tex_type = 'FLAME' and cfg.model.flame_tex_path = os.path.join(cfg.deca_dir, 'data', 'FLAME_texture.npz') > > FLAME_texture.npz download from https://flame.is.tue.mpg.de/index.html Where to download the FLAME_texture.npz file, why can't I...

Rendering

> > > change config decalib\utils\config.py > > > cfg.model.tex_type = 'FLAME' and cfg.model.flame_tex_path = os.path.join(cfg.deca_dir, 'data', 'FLAME_texture.npz') > > > FLAME_texture.npz download from https://flame.is.tue.mpg.de/index.html > > > > >...

how to calculate ms-ssim

1

the motion features Fk are taken as a concatenation of the output features and the downsampled warping flow

> Hi~ Thanks for your attention to our work! The shape b,128,H/8,W/8 can be first reshaped to b, 8_8_2,H/8,W/8 and then permuted to b, 2, H/8, 8, W/8, 8. In...

Do you plan to design a multi-contronet in diffuser?

> > Is [this](https://github.com/haofanwang/ControlNet-for-Diffusers#multi-controlnet-experimental) what you need? > > I have solved this problem, but the loading of model weights still needs some changes. I will merge it into this...