DECA icon indicating copy to clipboard operation
DECA copied to clipboard

DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)

Results 170 DECA issues
Sort by recently updated
recently updated
newest added

Why am I getting this effect? How to fix it? Input test image: ![0940_1](https://user-images.githubusercontent.com/30209916/172751205-3905fa82-346c-453b-8513-9b8a0e8d7e32.png) and the result as follow: ![0940_1_vis](https://user-images.githubusercontent.com/30209916/172751375-315489ac-0e1f-4815-bf2f-a0eee2ebf11b.jpg)

Hi all, When I run pip install -r requirements.txt I got error: ERROR: Could not find a version that satisfies the requirement torch==1.6.0 (from versions: 1.7.1, 1.8.0, 1.8.1, 1.9.0, 1.9.1,...

Bumps [opencv-python](https://github.com/skvark/opencv-python) from 4.1.1 to 4.2.0.32. Release notes Sourced from opencv-python's releases. 4.2.0.32 opencv-python: https://pypi.org/project/opencv-python/ opencv-contrib-python: https://pypi.org/project/opencv-contrib-python/ opencv-python-headless: https://pypi.org/project/opencv-python-headless/ opencv-contrib-python-headless: https://pypi.org/project/opencv-contrib-python-headless/ OpenCV version 4.2.0. Changes: macOS environment updated from xcode8.3...

dependencies

Hi. This is the output after a successful run: ``` creating the FLAME Decoder trained model found. load /home/onur/git-repos/DECA/data/deca_model.tar -- please check the results in TestSamples/examples/results 0it [00:00, ?it/s] ```...

![landmarks_51_annotated](https://user-images.githubusercontent.com/62639479/170710943-045199ea-5de6-48de-8164-24206a968f51.png) We want landmarks like this please help

Dear author, What kind of landmarks you use between 2DFAN or 3DFAN ? Though landmark fitting is operated on opdict['landmarks2d'], it seems right to use 2D FAN as gt, but...

When training, cropped face region with kpt68 will be scaled with randomly sample between 1.4 - 1.8, But the demo code uses "FAN" face detector scales cropped face with fixed...

Hi, thanks for making this great work open sourced. I want to know how to obtain the coordinates of 68 landmarks of the reconstructed model like (x,y,z) ? Thank you!

I cannot get it work, its seem wants cuda 10 i hear python only work with older version of cuda if have rtx 3090 and windows with miniconda, it will...