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

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.

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

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.

Convert from Basel Face Model (BFM) to the FLAME head model

Build your own ArcFace, CenterFace/Centernet

[CVPR 2024 Highlight] MonoNPHM: Dynamic Head Reconstruction from Monoculuar Videos

A tool to blur faces or other regions in images and videos 🤡🔍

3D face modeling and recognition using a depth camera (RGBD)

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.

Keras implementation of Face recognition using triplet loss