Bharat Bhatnagar

You'll have to download files from https://datasets.d2.mpi-inf.mpg.de/MultiGarmentNetwork/weights.zip and move them to the assests folder.

The difference between `SMPL_python_v1.1.0' and `SMPL_python_v1.0.0' are the number of shape parameters. In this project I used `SMPL_python_v1.0.0' with 10 shape parameters. File names are not important just ensure that...

Alternatively just save the smpl.faces in a numpy file and update the path.

Download from https://datasets.d2.mpi-inf.mpg.de/MultiGarmentNetwork/weights.zip and move to the assests folder.

Hi, you can use the following to convert rotation matrix to vector. https://docs.scipy.org/doc/scipy/reference/generated/scipy.spatial.transform.Rotation.html I haven't tested but a combination of 'from_matrix()' and 'as_rotvec()' should do the job.

The vertex labels are dependent on the garment classes present in your image. Eg. if your image has t-shirt and pants just take these entries from the test_data.pkl

> I'm still confused on this. Some help, please? > > Bharat [said](https://github.com/bharat-b7/MultiGarmentNetwork/issues/8#issuecomment-576364491): > > > vertexlabel is derived from the garment classes present in your image_x. Eg.: If the...

> Given pose estimation (via Openpose) and segmentation (via PGN) as well as manually set garment's category, is there existing code to convert these data to test_data.pkl? > > Maybe...

Hi, The template.obj is just SMPL model with 0 betas and pose. and faces.npy is just smpl faces, smpl.f You wouldn't need other things for the project. Feel free to...

Hi, I'm a bit tied till ICCV deadline. But in my experiments the pre-trained naked model works almost as good as the dressed one for dressed data. This works due...