LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking

🔥SLAM, VIsual localization, keypoint detection, Image matching, Pose/Object tracking, Depth/Disparity/Flow Estimation, 3D-graphic, etc. related papers and code

[IROS 2021] BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models

[NeurIPS'21] Unified tracking framework with a single appearance model. It supports Single Object Tracking (SOT), Video Object Segmentation (VOS), Multi-Object Tracking (MOT), Multi-Object Tracking and Segmentation (MOTS), Pose Tracking, Video Instance Segmentation (VIS), and class-agnostic MOT (e.g. TAO dataset).

[CVPR 2022 Oral] Official PyTorch Implementation of "GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras”.

Headless DeepLabCut (no GUI support)

Quickly add MediaPipe Pose Estimation and Detection to your iOS app. Enable powerful features in your app powered by the body or hand.

Mediapipe Pose Tracking AAR (android) Example

A native android application for pose estimation and detection using mlkit. The app can detect poses and recognize the pose made by the user.

Lela is a smart dietician who can help you to maintain diet and it also has Yoga posture detection feature where users can practice yoga at their home. https://lela-dietician.herokuapp.com

Implementing the ML Kit Pose Detection on stored video file

OpenPifPaf plugin for Posetrack

PoseNet Using Unity MLAgents Barracuda Engine

BlazePose: Body Segmentation for TFJS and NodeJS

juxtapose: Multi-Person Pose Tracking Inference SDK with RTMDet, YOLOv8, GDino, RTMPose (ONNX) & Trackers (ByteTrack & BotSORT) & Tapnet with custom ROIs + FastAPI GPU exe

[ECCV24] Keypoint Promptable Re-Identification: SOTA ReID method robust to occlusions and multi-person ambiguity

Unsupervised way for Pose guided Anime Video Generation using Generative Adversarial Networks.

Pose replication using Posenet

Deep Learning Approach for UWB Applications (IEEE Journal of Biomedical and Health Informatics)

A simple real-time 2D self-pose tracking algorithm using monocular visual odometry.