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
AaronJackson avatar

AaronJackson/vrn

0
View on GitHub↗
4,515 stars·743 forks·MATLAB·MIT·17 viewsaaronsplace.co.uk/papers/jackson2017recon↗

Vrn

vrn is a 3D face reconstruction tool that generates three-dimensional volumetric representations of human faces from single two-dimensional images. It utilizes a volumetric convolutional neural network regression model to predict 3D volume data directly from image pixels.

The system converts these volumetric predictions into 3D meshes through isosurface extraction and vertex coloring. It further applies realistic surface details by mapping two-dimensional image pixels onto the resulting 3D mesh using nearest-neighbor texture projection.

The project provides capabilities for single-image depth estimation and digital human modeling.

Features

  • Single-Image 3D Reconstructions - Generates complete 3D volumetric representations of human faces from a single two-dimensional input image.
  • Direct Voxel Prediction - Implements a volumetric CNN regression model that predicts 3D volume data directly from image pixels.
  • Volumetric Regression Architectures - Implements a deep learning architecture that predicts 3D volume data directly from 2D image inputs.
  • Volumetric CNN Regression - Utilizes a volumetric convolutional neural network regression model to predict 3D volume data from pixels.
  • 3D Face Reconstruction - Provides a system for generating 3D volumetric representations of human faces from single 2D images.
  • Volumetric Reconstruction Tools - Provides a tool for creating dense volumetric 3D face models from single images.
  • Monocular Depth Estimators - Infers three-dimensional spatial depth and volume from single 2D facial photographs.
  • Human Digitalization - Generates 3D meshes with realistic surface textures suitable for digital human modeling.
  • Isosurface Extractors - Converts volumetric predictions into 3D meshes by calculating the isosurface and applying vertex colors.
  • Image-to-3D Texture Engines - Transfers 2D image textures onto 3D digital face representations using nearest-neighbor sampling.
  • Volumetric Mesh Extraction - Converts volumetric density fields into discrete polygonal triangle meshes through isosurface extraction.
  • Texture Projection Mapping - Maps 2D image pixels onto the resulting 3D mesh using nearest-neighbor projection for realistic surface details.
  • Texture Sampling - Projects colors from 2D images onto a 3D mesh using nearest-neighbor pixel sampling.
  • Face Alignment And Reconstruction - Volumetric CNN regression for 3D reconstruction from single images.
  • Generative Models - Volumetric CNN regression for 3D face reconstruction.
  • Faces: - Listed in the “Faces:” section of the Curated List Of Awesome 3D Morphable Model Software And Data awesome list.

Star history

Star history chart for aaronjackson/vrnStar history chart for aaronjackson/vrn

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 Vrn

These projects share indexed features with Vrn. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • cleardusk/3ddfacleardusk avatar

    cleardusk/3DDFA

    3,678View on GitHub↗

    3DDFA is a 3D face reconstruction tool that generates three-dimensional facial meshes and 68 structural landmarks from a single two-dimensional input image. The project provides utilities for estimating facial pose and depth maps to determine the orientation and position of a face. It includes a geometry exporter to save reconstructed facial shapes into standard file formats for use in external 3D modeling software. The software further covers automated face cropping using landmark-based and landmark-free identification methods, as well as the extraction of specialized mathematical represent

    Python
    View on GitHub↗3,678
  • xxlong0/wonder3dxxlong0 avatar

    xxlong0/Wonder3D

    5,388View on GitHub↗

    Wonder3D is a diffusion-based system for single image 3D reconstruction. It generates high-detail 3D meshes from a single input image by producing consistent multi-view normal maps and color images. The pipeline functions as a multi-view normal map generator and a textured mesh extractor. It uses cross-domain multi-view synthesis to create view-dependent maps, which are then converted into 3D geometry through radiance fusion and memory-efficient surface reconstruction. The project covers 3D mesh generation, multi-view generation, and textured 3D modeling. It also includes capabilities for tr

    Python3d-aigc3d-generation3dgeneration
    View on GitHub↗5,388
  • facebookresearch/pifuhdfacebookresearch avatar

    facebookresearch/pifuhd

    9,743View on GitHub↗

    pifuhd is a 3D human reconstruction framework that generates high-resolution 3D meshes of people from a single 2D image. It utilizes pixel-aligned implicit functions to map image pixels to 3D space, predicting surface occupancy and distance to create detailed geometry. The system includes a pipeline for creating digital human assets, moving from 2D image feature projection to the extraction of discrete triangular meshes. It features specialized tools for refining these models, including a post-processor that removes geometric artifacts by isolating the largest connected component of the mesh.

    Python
    View on GitHub↗9,743
  • yadiraf/prnetYadiraF avatar

    YadiraF/PRNet

    5,013View on GitHub↗

    PRNet is a Python library for 3D facial reconstruction. It uses a deep learning regression model to predict 3D facial geometry and vertex colors from a single 2D input image to generate a textured mesh. The project provides tools for digital face swapping, allowing the replacement of a target face with a new image and blending textures to match the original pose. It also includes a framework for face texture swapping and blending to fit specific 3D poses. Additional capabilities cover facial analysis, including the detection and alignment of facial landmarks and the estimation of head pose a

    Python
    View on GitHub↗5,013
Compare all 30 related projects→

Frequently asked questions

What does aaronjackson/vrn do?

vrn is a 3D face reconstruction tool that generates three-dimensional volumetric representations of human faces from single two-dimensional images. It utilizes a volumetric convolutional neural network regression model to predict 3D volume data directly from image pixels.

What are the main features of aaronjackson/vrn?

The main features of aaronjackson/vrn are: Single-Image 3D Reconstructions, Direct Voxel Prediction, Volumetric Regression Architectures, Volumetric CNN Regression, 3D Face Reconstruction, Volumetric Reconstruction Tools, Monocular Depth Estimators, Human Digitalization.

Which projects share features with aaronjackson/vrn?

Projects with overlapping indexed features include: cleardusk/3ddfa — 3DDFA is a 3D face reconstruction tool that generates three-dimensional facial meshes and 68 structural landmarks from… xxlong0/wonder3d — Wonder3D is a diffusion-based system for single image 3D reconstruction. It generates high-detail 3D meshes from a… facebookresearch/pifuhd — pifuhd is a 3D human reconstruction framework that generates high-resolution 3D meshes of people from a single 2D… yadiraf/prnet — PRNet is a Python library for 3D facial reconstruction. It uses a deep learning regression model to predict 3D facial… nv-tlabs/get3d — GET3D is a generative 3D mesh model and rendering framework designed to synthesize high-quality textured shapes and… vt-vl-lab/3d-photo-inpainting — This project is an RGB-D image inpainting tool and framework for 3D photo reconstruction. It transforms single 2D…