Arthur151/ROMP
PyTorch library for monocular multi-person 3D human pose estimation and mesh recovery in real time.
Not currently ranked — collecting fresh signals.
star history
ROMP provides a one-stage approach for extracting 3D human meshes and poses from single-camera images. The project includes multiple research works (ROMP, BEV, TRACE) for multi-person 3D reconstruction, depth estimation, and temporal tracking. It offers cross-platform APIs and supports exporting results to common 3D formats (FBX, GLB, BV). Built on PyTorch with SMPL body model integration.
Frequently asked
- What is Arthur151/ROMP?
- PyTorch library for monocular multi-person 3D human pose estimation and mesh recovery in real time.
- Is ROMP open source?
- Yes — Arthur151/ROMP is open source, released under the Apache-2.0 license.
- What language is ROMP written in?
- Arthur151/ROMP is primarily written in Python.
- How popular is ROMP?
- Arthur151/ROMP has 1.5k stars on GitHub.
- Where can I find ROMP?
- Arthur151/ROMP is on GitHub at https://github.com/Arthur151/ROMP.