-
Hi. thanks for sharing the nice work.
In your code, You use SMPLify-X pseudo GT on 3D datasets(H36M, MuCo), and use Neural Annot pseudo GT on 2D datasets(CrowdPose, MSCOCO).
Can I ask why you don'…
-
Hi, thanks for your contribution.
The issue is that I can't run demo.py for neutral model since SMPL project website doesn't provide
neutral model pkl. Do you have any source for it?
-
Hi, I'm trying to render the ExPose output on a web renderer for divulgation purposes.
I'm facing a problem with alignment between the original image and the generated model. Basically I want to ge…
-
When doing the following command:
`.\zluda-3-windows\zluda\zluda.exe 'EasyMocap\python apps/demo/mv1p.py examples --out examples/output/smpl --vis_det --vis_repro --undis --sub_vis 1 7 13 19 --vis_…
-
I'm running the demo as readme. The output garment meshes look nice, but why does the smpl mesh mismatch with them?
 trying to build up my own motion data. In the 4.Transfer SMPL step. I encounter the fol…
-
hello @vchoutas,
I wish to know can I directly use the 3d ground-truth key points of H36m and develop the smpl parameters instead of using the 2d joints and images.
Inform me of any necessary c…
-
Executing...
`python3 smplifyx/main.py --config cfg_files/fit_smpl.yaml --data_folder ~/dev/smpl_test_data --output_folder ~/dev/smpl_test_data --visualize="False" --model_folder ~/dev/models/SMPL_…
-
Hi, @Luke-Luo1
Thanks for your fantastic work! I eagerly wonder how to extract manual and kinetic feature for aist++ pkl data(train/test)?
I am aware of the difference between popdg dataset and ais…
-
I am using [Multi Garment Network](https://github.com/bharat-b7/MultiGarmentNetwork/), a method which can clothe an SMPL model. The garments are instances of the [psbody.Mesh class](https://github.com…