morphable-model

This codebase demonstrates how to synthesize realistic 3D character animations given an arbitrary speech signal and a static character mesh.

The idea of this list is to collect shared data and algorithms around 3D Morphable Models. You are invited to contribute to this list by adding a pull request. The original list arised from the Dagstuhl seminar on 3D Morphable Models https://www.dagstuhl.de/19102 in March 2019.

Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

Example code for the FLAME 3D head model. The code demonstrates how to sample 3D heads from the model, fit the model to 3D keypoints and 3D scans.

Tensorflow framework for the FLAME 3D head model. The code demonstrates how to sample 3D heads from the model, fit the model to 2D or 3D keypoints, and how to generate textured head meshes from Images.

A high-fidelity 3D face reconstruction library from monocular RGB image(s)

This is a implementation of the 3D FLAME model in PyTorch

Official repository accompanying a CVPR 2022 paper EMOCA: Emotion Driven Monocular Face Capture And Animation. EMOCA takes a single image of a face as input and produces a 3D reconstruction. EMOCA sets the new standard on reconstructing highly emotional images in-the-wild

Project Page of Synthesizing Normalized Faces From Facial Identity Features - [CVPR 2017]

Blender Add-on for the FLAME face model

The provided program loads a multilinear face model and fits this model to a point cloud or a triangle mesh.

Fixed version of https://github.com/tomguluson92/PRNet_PyTorch

The provided program loads a multilinear wavelet model and fits this model to a point cloud or a triangle mesh.

Flexible Object Reconstruction from Multiple Silhouettes. Cashman & Fitzgibbon, 'What Shape are Dolphins? Building 3D Morphable Models from 2D Images', 2012. Updated 2018, Jason Manley.

The provided program jointly optimizes a multilinear face model and the registration of the face scans used for model training.

Basel morphable face model mesh and texture generator using GPU.

The program loads a global or a local linear statistical face model and fits it to a point cloud or triangle mesh.

Visualize 3d meshes via scripting in scheme

The provided program robustly learns a multilinear face model from databases with missing data, corrupt data, wrong semantic correspondence, and inaccurate vertex correspondence.

Blender add-on to implement VOCA neural network.