FORTH-ModelBasedTracker / MocapNET
We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance
RepositoryStats indexes 565,279 repositories, of these FORTH-ModelBasedTracker/MocapNET is ranked #58,646 (90th percentile) for total stargazers, and #61,482 for total watchers. Github reports the primary language for this repository as C++, for repositories using this language it is ranked #3,172/30,279.
FORTH-ModelBasedTracker/MocapNET has Github issues enabled, there are 17 open issues and 104 closed issues.
Homepage URL: https://www.youtube.com/watch?v=Jgz1MRq-I-k
Star History
Github stargazers over time
Watcher History
Github watchers over time, collection started in '23
Recent Commit History
64 commits on the default branch (master) since jan '22
Yearly Commits
Commits to the default branch (master) per year
Issue History
Languages
The primary language is C++ but there's also others...
updated: 2024-09-27 @ 11:53am, id: 195396337 / R_kgDOC6WC8Q