Skip to main content
zenodoopen

AUTH-OpenDR SMPL+D Human Bodies Dataset

<p>The&nbsp;&nbsp;dataset contains 2982 human bodies&nbsp;in various shapes and textures folowing the&nbsp;SMPL-D template. At its core, our dataset&nbsp; consists of 183 unique SMPL+D bodies, which were generated through non-rigid shape registration of manually generated MakeHuman models. The rest were generated by applying shape and texture alterations to those models.&nbsp;In addition, we provide code for converting those human models in the FBX format.&nbsp; However, pose-dependent deformations are not applied to the human models.&nbsp;Finally, instructions for setting a demo project in the Webots simulator are provided. In the project, one the SMPL+D models in FBX format can perform an animation from AMASS.</p> <p>The dataset was developed by Aristotle University of Thessaloniki (AUTH) within the H2020 OpenDR Project.</p> <p>The dataset is available through the official GitHub repository of the OpenDR toolkit <a href="https://github.com/opendr-eu/opendr/tree/master/projects/python/simulation/SMPL%2BD_human_models">here</a>.</p>

ShareScore

36/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
8
Harmonization
4
Access
16
Reuse readiness
0
Engagement
8

Topics