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
·
mkocabas avatar

mkocabas/VIBE

0
View on GitHub↗
3,157 stars·576 forks·Python·other·14 viewsarxiv.org/abs/1912.05656↗

VIBE

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 machine learning operations for model training. The framework supports multi-person sequence detection and parametric shape optimization to align 3D meshes with 2D detections.

Features

  • Pose Estimation Frameworks - Provides a comprehensive framework for predicting body model parameters to reconstruct the physical pose and shape of multiple people.
  • 3D Pose Estimation - Converts 2D video detections into three-dimensional spatial coordinates to reconstruct human body movement.
  • Body-Hand-Face Reconstructions - Fits the SMPL parametric body model to video footage to extract 3D body poses and shapes.
  • Parametric Human Model Fitting - Optimizes parameters of pre-defined human body meshes to align 3D reconstructions with 2D detections.
  • Video Pose Estimation - Implements techniques for tracking and predicting human motion across temporal video sequences to create continuous trajectories.
  • 3D Pose Model Training - Includes a pipeline for preparing datasets and training neural networks specifically for 3D joint and shape estimation.
  • Multi-Person Trackers - Identifies and tracks multiple distinct human figures across video frames to estimate independent body poses.
  • Format Exporters - Converts predicted pose sequences into standard 3D animation file formats for use in external graphics software.
  • Motion Data Export Tools - Provides tools to export reconstructed 3D human motion data into standard animation file formats for use in graphics software.
  • 3D Human Mesh Recovery - Video-based human mesh recovery from monocular video.

Star history

Star history chart for mkocabas/vibeStar history chart for mkocabas/vibe

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

Open-source alternatives to VIBE

Similar open-source projects, ranked by how many features they share with VIBE.
  • zju3dv/easymocapzju3dv avatar

    zju3dv/EasyMocap

    4,483View on GitHub↗

    EasyMocap is a markerless 3D human motion capture system that recovers body, hand, and face poses from single or multi-view video without physical markers or suits. It uses parametric body models like SMPL, SMPL-X, and MANO, and leverages mirror reflections to resolve depth ambiguity in single-view pose estimation, improving accuracy by computing mirror surface normals from vanishing points. The system distinguishes itself through mirror-assisted depth disambiguation, enabling accurate 3D pose reconstruction from a single RGB image or video that includes a mirror reflection. It also supports

    Pythonmotion-capture
    View on GitHub↗4,483
  • 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
  • facebookresearch/sam-3d-bodyfacebookresearch avatar

    facebookresearch/sam-3d-body

    2,628View on GitHub↗

    sam-3d-body is a machine learning framework for 3D human mesh recovery and pose estimation. It utilizes a 3D human mesh recovery model to reconstruct full-body meshes, including the body, hands, and feet, from a single image. The project implements a specialized extension of the Segment Anything Model to guide the extraction and refinement of human body shapes. This integration allows for prompt-guided mesh recovery, where 2D masks and keypoints constrain the inference of 3D pose and shape parameters. The system covers a range of computer vision capabilities, including 3D spatial alignment t

    Python
    View on GitHub↗2,628
  • facebookresearch/denseposefacebookresearch avatar

    facebookresearch/DensePose

    7,252View on GitHub↗

    DensePose is a 3D human pose estimation framework designed to map 2D image pixels to a 3D surface-based model of the human body in real time. It functions as a computer vision anatomical mapper that projects 2D visual data onto a 3D surface to create detailed anatomical representations. The system operates as an image-to-3D texture transfer engine, localizing 2D image annotations onto 3D models to apply photographic textures to digital human representations. It uses a surface-based body mapping method to associate human pixels in an RGB image with specific coordinates on a 3D body template.

    Jupyter Notebook
    View on GitHub↗7,252
See all 30 alternatives to VIBE→

Frequently asked questions

What does mkocabas/vibe do?

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.

What are the main features of mkocabas/vibe?

The main features of mkocabas/vibe are: Pose Estimation Frameworks, 3D Pose Estimation, Body-Hand-Face Reconstructions, Parametric Human Model Fitting, Video Pose Estimation, 3D Pose Model Training, Multi-Person Trackers, Format Exporters.

What are some open-source alternatives to mkocabas/vibe?

Open-source alternatives to mkocabas/vibe include: zju3dv/easymocap — EasyMocap is a markerless 3D human motion capture system that recovers body, hand, and face poses from single or… mvig-sjtu/alphapose — AlphaPose is a deep learning pose estimation framework and PyTorch computer vision library designed for detecting and… facebookresearch/sam-3d-body — sam-3d-body is a machine learning framework for 3D human mesh recovery and pose estimation. It utilizes a 3D human… facebookresearch/densepose — DensePose is a 3D human pose estimation framework designed to map 2D image pixels to a 3D surface-based model of the… open-mmlab/mmpose — MMPose is a PyTorch-based pose estimation toolbox and deep learning training pipeline designed for detecting 2D and 3D… facebookresearch/videopose3d — VideoPose3D is a machine learning framework designed for 3D human pose estimation. It functions as a motion…