How to get h36m_single_train_openpose.npz? about spin HOT 13 CLOSED

We used pose and shape parameters generated by the MoSh method. However, due to license implications, this data is not public. You could try to fit SMPL to the 3D keypoints of the dataset. This would probably be less accurate, but it should give you reasonable results.

from spin.

No MoSh results are available for MPI-INF-3DHP. In that case, we fit SMPL to keypoints. Since ground truth is not very accurate, we prefer to use OpenPose predictions and fit SMPL to them for all viewpoints simultaneously.

from spin.

@geopavlakos @BICHENG @liwenssss @vigorbird @GuiZhaoyang
where can i get the json file in the code
json_file = os.path.join(openpose_path, 'coco', imgname.replace('.jpg', '_keypoints.json'))

from spin.

This file includes the data for Human3.6M and is similar to the other .npz files we released. Besides image names, scale/center and 2D/3D/openpose joints, it also includes pose and shape parameters for the Human3.6M dataset. Due to the dataset license, we cannot release it, but if you have the data, it should be straightforward to produce it, if you also take a look to the other dataset preprocessing scripts we provide.

from spin.

Could you please add this h36m script to this repository?

from spin.

The script is already in SPIN/datasets/preprocess/h36m_train.py. I updated it to include the reading of the openpose predictions, but you will still need to read and include the SMPL pose and shape parameters in the .npz file (in case you have access to them).

from spin.

if I have h36m dataset , how can I generate pose and betas paramers?

from spin.

Do you generate pose and shape parameters of MPI-INF-3DHP in the same way?

from spin.

from spin.

The code for the MoSh approach is not publicly available. You could refer to the description of the paper for more details.

from spin.

@geopavlakos hi,Could I know how to fit SMPL to the 3D keypoints of the h36m dataset?Because I have not the Mocap annotation but I have the 3D keypoints annotation.May I know the code to to fit SMPL to the 3D keypoints?

from spin.

@GuiZhaoyang 兄弟留个邮箱，有偿求human3.6m mosh数据

from spin.

No MoSh results are available for MPI-INF-3DHP. In that case, we fit SMPL to keypoints. Since ground truth is not very accurate, we prefer to use OpenPose predictions and fit SMPL to them for all viewpoints simultaneously.

Hi @geopavlakos et al., Could you kindly release openpose detection of these data please? Thx & best,

from spin.