There are 3 repositories under pose topic.
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
深度学习入门课、资深课、特色课、学术案例、产业实践案例、深度学习知识百科及面试题库The course, case and knowledge of Deep Learning and AI
PyTorch implementation of our ICCV 2019 paper: Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis
YOLOv8 using TensorRT accelerate !
A PyTorch toolkit for 2D Human Pose Estimation.
NumPy, TensorFlow and PyTorch implementation of human body SMPL model and infant body SMIL model.
VPoser: Variational Human Pose Prior
[CVPR19] FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation from a Single Image
Official Pytorch implementation of 6DRepNet: 6D Rotation representation for unconstrained head pose estimation.
a toolkit for pose estimation using deep learning
MediaPipeのPythonパッケージのサンプルです。2024/9/1時点でPython実装のある15機能について用意しています。
MediaPipeで姿勢推定を行い、Tokyo2020オリンピック風のピクトグラムを表示するデモ
[ ICCV 2021 Oral ] Our method can estimate camera poses and neural radiance fields jointly when the cameras are initialized at random poses in complex scenarios (outside-in scenes, even with less texture or intense noise )
Implementation of Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields
BlazePoseBarracuda is a human 2D/3D pose estimation neural network that runs the Mediapipe Pose (BlazePose) pipeline on the Unity Barracuda with GPU.
Parse and visualize asf/amc files from CMU MoCap dataset.
Keras-tensorflow implementation of PersonLab (https://arxiv.org/abs/1803.08225)
Official Pytorch implementation of "Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimation" IEEE TIP 24
Using A.I. and computer vision to build a virtual personal fitness trainer. (Most Startup-Viable Hack - HackNYU2018)
Based on tensorrt v8.0+, deploy detect, pose, segment, tracking of YOLOv8 with C++ and python api.
Code for ACCV 2020 "Speech2Video Synthesis with 3D Skeleton Regularization and Expressive Body Poses"
6D Pose Annotation Tool and Real-time Visualization - Vision6D for supporting users to annotate the 6D pose of a given 3D object for any given 2D images and depth estimation. This 6D pose annotation tool supports annotate videos and a set of 2D images.
A Perspective-n-Points-and-Lines method.
React App for creating pretty gradients, intuitively
Machine-Learning powered Virtual Camera with SVG Animation (alpha)
Use Deepstream python API to extract the model output tensor and customize the post-processing of YOLO-Pose
Motion Averaging
PyTorch implementation for 3D human pose estimation base on ROS
Gesture-controlled Video Game. Just swing your finger and play the game without touching your PC