PyMAF
metrabs
| PyMAF | metrabs | |
|---|---|---|
| 1 | 1 | |
| 581 | 424 | |
| - | - | |
| 3.6 | 3.4 | |
| 4 months ago | about 1 month ago | |
| Python | Python | |
| GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
PyMAF
metrabs
-
UE4 Tutorial - AI Motion Capture From a Single Video (updated!)
This isn't for blender but you're right there's already lots of open source implementations of AI motion capture that are probably just as good as OPs, here's one I found https://github.com/isarandi/metrabs
What are some alternatives?
Lifting-from-the-Deep-release - Implementation of "Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image"
blender-retarget - Applies animation from one armature to another
DeepHuman - Code for our ICCV paper "DeepHuman: 3D Human Reconstruction from a Single Image"
yolo-tf2 - yolo(all versions) implementation in keras and tensorflow 2.x
HuManiFlow - [CVPR 2023] Code repository for HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation
evopose2d - EvoPose2D is a two-stage human pose estimation model that was designed using neuroevolution. It achieves state-of-the-art accuracy on COCO.
AvatarPoser - Official Code for ECCV 2022 paper "AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing"
3DMPPE_POSENET_RELEASE - Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019
posenet-python - A Python port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)