Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update README.md #406

Merged
merged 4 commits into from
Feb 13, 2023
Merged

Update README.md #406

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8665c45
Update README.md
charsyme Feb 10, 2023
81f7b80
Update projects/python/simulation/SMPL+D_human_models/README.md
charsyme Feb 10, 2023
068ba2a
Update README.md
charsyme Feb 10, 2023
910f7b4
Update README.md
charsyme Feb 10, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions projects/python/simulation/SMPL+D_human_models/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,8 @@ This folder contains code for:

### Download the raw SMPL+D models only (≈12.5Gb)

[SMPL](https://files.is.tue.mpg.de/black/papers/SMPL2015.pdf) is a parametric statistical body shape model. SMPL+D is an extension of SMPL, which can encode shape deformations from clothes and hair as vertex displacements. Our dataset contains more that 3200 human models in various shapes and textures. At its core, our dataset is consisted of more than 200 unique SMPL+D models, which were generated through non-rigid shape registration of [MakeHuman](https://www.google.com/search?channel=fs&client=ubuntu&q=makehuman) models. The rest were generated by applying shape and texture deformations to those models. For each human model in our dataset, we provide its corresponding:
[SMPL](https://files.is.tue.mpg.de/black/papers/SMPL2015.pdf) is a parametric statistical body shape model. SMPL+D is an extension of SMPL, which can encode shape deformations from clothes and hair as vertex displacements. Our dataset contains 2914 human models in various shapes and textures. At its core, our dataset consists of 183 unique SMPL+D models, which were generated through non-rigid shape registration of [MakeHuman](https://www.google.com/search?channel=fs&client=ubuntu&q=makehuman) models. The rest were generated by applying shape and texture deformations to those models. For each human model in our dataset, we provide its corresponding:


- Gender
- Shape Parameters (betas)
Expand Down Expand Up @@ -65,7 +66,7 @@ $BLENDER_PATH/blender -P src/generate_models.py

**Note:** FBX models must have been previously generated

Finally, instructions for setting a demo project in Webots are provided. In the project, one the SMPL+D models in FBX format can perform an animation from [AMASS](https://smpl.is.tue.mpg.de/).
Finally, instructions for setting a demo project in Webots are provided. In the project, the SMPL+D models (in the FBX format) can perform animations from [AMASS](https://smpl.is.tue.mpg.de/).

- Download ACCAD database from AMASS (https://amass.is.tue.mpg.de/download.php)

Expand Down