Pose Estimation Projects
Pose Estimation is a domain in computer vision where we detect and track the location and orientation of an object. Human Pose Estimation is the task to estimate the pose of a person from an image or a video by estimating the spatial locations of key body joints (keypoints - elbows, wrists, etc.). It can be used in applications such as action recognition, animation, gaming and in sport analytics as well.
In the list below, we highlight 10+ interesting repositories, which share their pose estimation projects.
| AlexEMG/DeepLabCut | Markerless pose estimation of user-defined features with deep learning for all animals, including humans |
| CMU-Perceptual-Computing-Lab/openpose | OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation |
| facebookresearch/VideoPose3D | Efficient 3D human pose estimation in video using 2D keypoint trajectories |
| ildoonet/tf-pose-estimation | Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference. |
| j96w/DenseFusion | “DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion” code repository |
| MVIG-SJTU/AlphaPose | Real-Time and Accurate Multi-Person Pose Estimation&Tracking System |
| vita-epfl/openpifpaf | Official implementation of “PifPaf: Composite Fields for Human Pose Estimation” in PyTorch. |
| xinghaochen/awesome-hand-pose-estimation | Awesome work on hand pose estimation/tracking |
| xingyizhou/CenterNet | Object detection, 3D detection, and pose estimation using center point detection: |
| ZheC/Realtime_Multi-Person_Pose_Estimation | Code repo for realtime multi-person pose estimation in CVPR'17 (Oral) |
| zju3dv/mvpose | Code for “Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views” in CVPR'19 |
