awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
facebookresearch avatar

facebookresearch/VideoPose3DArchived

0
View on GitHub↗
3,986 stars·782 forks·Python·other·23 views

VideoPose3D

VideoPose3D is a machine learning framework designed for 3D human pose estimation. It functions as a motion reconstruction tool that predicts 3D joint positions from 2D video sequences using a temporal convolutional network to process body movement over time.

The project includes a semi-supervised learning pipeline that improves pose accuracy by combining labeled datasets with unlabeled video data and projection consistency loss. It also features a video pose visualizer capable of rendering 3D skeleton reconstructions and 2D keypoints as overlays on original footage.

The framework covers the full lifecycle of motion analysis, including 3D pose model training, biometric motion validation against ground truth data, and the generation of visual predictions in GIF or MP4 formats.

Features

  • 3D Pose Estimation - Provides a framework for converting 2D pose detections from video into three-dimensional spatial coordinates.
  • Motion Reconstruction - Implements algorithms to convert visual tracking data into 3D skeletal motion coordinates.
  • Semi-supervised Learning Pipelines - Features a training pipeline that processes labeled and unlabeled video data simultaneously using projection consistency loss.
  • Temporal Convolutional Networks - Employs a temporal convolutional network architecture to reconstruct 3D body movement over time.
  • Temporal Pose Analysis - Uses temporal convolutions to estimate human motion over time from video sequences.
  • Custom Video Inference - Enables the analysis of original video files to calculate 3D human poses in real-world environments.
  • 3D Pose Reconstruction - Visualizes the mapping of 2D tracking data into three-dimensional skeletal space for validation.
  • Pose Estimation Validation - Includes routines for verifying the precision of pose reconstructions against ground truth biometric data.
  • 3D Pose Model Training - Develops models that estimate 3D joint positions from 2D detections using temporal convolutions.
  • Model Validation Tools - Includes utilities to verify reconstruction precision against specific subjects or actions using saved checkpoints.
  • Pose Visualizations - Provides a visualizer for rendering 3D skeleton reconstructions and 2D keypoints as video overlays.
  • Visual Overlays - Generates MP4 or GIF overlays of 3D model predictions onto original video footage.

Star history

Star history chart for facebookresearch/videopose3dStar history chart for facebookresearch/videopose3d

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Projects sharing features with VideoPose3D

These projects share indexed features with VideoPose3D. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • mvig-sjtu/alphaposeMVIG-SJTU avatar

    MVIG-SJTU/AlphaPose

    8,583View on GitHub↗

    AlphaPose is a deep learning pose estimation framework and PyTorch computer vision library designed for detecting and tracking human body, face, hand, and foot keypoints in images and videos. It provides a system for skeletal posture estimation and multi-person pose tracking. The project implements tools for three-dimensional human pose reconstruction, generating joint positions and body mesh shapes from two-dimensional image data. It also includes a multi-person pose tracker capable of maintaining the identity of multiple people across consecutive video frames. The framework covers a broad

    Python
    View on GitHub↗8,583
  • open-mmlab/mmposeopen-mmlab avatar

    open-mmlab/mmpose

    7,374View on GitHub↗

    MMPose is a PyTorch-based pose estimation toolbox and deep learning training pipeline designed for detecting 2D and 3D keypoints on humans, animals, and faces. It serves as a computer vision model zoo and a framework for both 2D pose estimation and 3D pose lifting. The project is distinguished by its modular architecture and extensibility, employing a registry-based system and hierarchical configurations to allow for custom algorithm integration and model pipeline customization. It supports diverse estimation paradigms, including top-down, bottom-up, and two-stage pose lifting workflows. The

    Pythonanimal-pose-estimationbenchmarkcpm
    View on GitHub↗7,374
  • mkocabas/vibemkocabas avatar

    mkocabas/VIBE

    3,157View on GitHub↗

    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

    Python3d-human-pose3d-pose-estimationcvpr
    View on GitHub↗3,157
  • cmu-perceptual-computing-lab/openposeCMU-Perceptual-Computing-Lab avatar

    CMU-Perceptual-Computing-Lab/openpose

    34,145View on GitHub↗

    OpenPose is a real-time pose estimation engine designed to detect and track human body, face, hand, and foot landmarks. It functions as a multi-person motion tracker, identifying the spatial coordinates of multiple individuals simultaneously within video streams or static images. Beyond two-dimensional detection, the software acts as a three-dimensional kinematics processor, reconstructing spatial movement data from single or multiple synchronized camera perspectives. The system distinguishes itself through a bottom-up approach that utilizes part-affinity fields to associate body parts across

    C++caffecomputer-visioncpp
    View on GitHub↗34,145
Compare all 30 related projects→

Frequently asked questions

What does facebookresearch/videopose3d do?

VideoPose3D is a machine learning framework designed for 3D human pose estimation. It functions as a motion reconstruction tool that predicts 3D joint positions from 2D video sequences using a temporal convolutional network to process body movement over time.

What are the main features of facebookresearch/videopose3d?

The main features of facebookresearch/videopose3d are: 3D Pose Estimation, Motion Reconstruction, Semi-supervised Learning Pipelines, Temporal Convolutional Networks, Temporal Pose Analysis, Custom Video Inference, 3D Pose Reconstruction, Pose Estimation Validation.

Which projects share features with facebookresearch/videopose3d?

Projects with overlapping indexed features include: mvig-sjtu/alphapose — AlphaPose is a deep learning pose estimation framework and PyTorch computer vision library designed for detecting and… open-mmlab/mmpose — MMPose is a PyTorch-based pose estimation toolbox and deep learning training pipeline designed for detecting 2D and 3D… mkocabas/vibe — VIBE is a 3D human pose estimation framework designed to reconstruct human body shapes and poses from video frames. It… cmu-perceptual-computing-lab/openpose — OpenPose is a real-time pose estimation engine designed to detect and track human body, face, hand, and foot… leoxiaobin/deep-high-resolution-net.pytorch — This project is a PyTorch implementation of a research architecture designed for high-resolution representation… deeplabcut/deeplabcut — DeepLabCut is a deep learning toolkit for markerless 2D and 3D animal pose estimation. It functions as a motion…