UPC-ViRVIG/DragPoser
Official Code for Eurographics 2025 paper "DragPoser: Motion Reconstruction from Variable Sparse Tracking Signals via Latent Space Optimization"
DragPoser helps animators, game developers, or researchers reconstruct full human body motion from sparse tracking signals. You provide a BVH file containing limited tracker data, and it outputs a complete, realistic motion sequence. This tool is ideal for anyone working with motion capture data that is incomplete or low-resolution.
No commits in the last 6 months.
Use this if you need to generate realistic, full-body human motion from sparse or incomplete motion capture data.
Not ideal if you already have high-fidelity, complete motion capture data and do not need to reconstruct missing information.
Stars
13
Forks
2
Language
Python
License
MIT
Category
Last pushed
Feb 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/UPC-ViRVIG/DragPoser"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
talmolab/sleap
A deep learning framework for multi-animal pose tracking.
kennymckormick/pyskl
A toolbox for skeleton-based action recognition.
open-mmlab/mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
jgraving/DeepPoseKit
a toolkit for pose estimation using deep learning
DenisTome/Lifting-from-the-Deep-release
Implementation of "Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image"