Awesome GitHub RepositoriesVideo Pose Estimation

AlphaPose es un framework de estimación de pose basado en deep learning y una biblioteca de visión artificial para PyTorch, diseñada para detectar y rastrear puntos clave del cuerpo humano, rostro, manos y pies en imágenes y videos. Proporciona un sistema para la estimación de posturas esqueléticas y el seguimiento de poses de múltiples personas. El proyecto implementa herramientas para la reconstrucción de poses humanas en tres dimensiones, generando posiciones de articulaciones y mallas corporales a partir de datos de imágenes bidimensionales. También incluye un rastreador de poses multi-persona capaz de mantener la identidad de varios individuos a través de fotogramas de video consecutivos. El framework cubre una amplia gama de capacidades de visión artificial, incluyendo la localización de puntos clave en múltiples personas, el seguimiento de movimiento humano y la reconstrucción de mallas corporales en 3D.

VIBE is a 3D human pose estimation framework designed to reconstruct human body shapes and poses from video frames. It functions as a toolkit for predicting parameters of the SMPL human body model to generate 3D mesh sequences. The system includes a 3D motion data exporter to convert predicted pose sequences into standard 3D file formats for use in graphics and animation software. It also provides a structured training pipeline for preparing datasets and training models to estimate body shapes from images. Its capabilities cover computer vision for estimating body pose and shape, as well as

The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"

The implementation of an algorithm presented in the CVPR18 paper: "Detect-and-Track: Efficient Pose Estimation in Videos"

This is the implementation of the approach described in the paper:

This software is provided as a supplementary material for our CVPR'18 and TPAMI'20 papers:

This is the code for the paper

This is the code for the CVPR 2018 paper Neural Kinematic Networks for Unsupervised Motion Retargetting by Ruben Villegas, Jimei Yang, Duygu Ceylan and Honglak Lee.

JTA (Joint Track Auto) is a huge dataset for pedestrian pose estimation and tracking in urban scenarios created by exploiting the highly photorealistic video game Grand Theft Auto V. We collected a set of 512 full-HD videos (256 for training and 256 for testing), 30 seconds long, recorded at 30…

This package contains code for the Deep Multitask Human Sensing (DMHS) method, published in the CVPR 2017 paper Deep Multitask Architecture for Integrated 2D and 3D Human Sensing.

This repository contains the code for performing warping of time series using Tensorflow. It also contains the code of computing the inverse of warping functions in Tensorflow