Stars
[Official Code] Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction
OFER: Occluded Face Expression Reconstruction. A 3D face reconstruction method producing diverse plausible expressive faces from a single-view occluded image.
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.
The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.
The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.
Official code for ICLR25 "TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction"
Papers, Datasets, Benchmarks for 3D Face (Reconstruction, Talking head, etc)
Official Pytorch Implementation of SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024)
[CVPRW 2022] Delving into High-Quality Synthetic Face Occlusion Segmentation Datasets
A Visual Tools of Basel Face Model using Qt5(+built-in OpenGL) and C++
FaceScape (PAMI2023 & CVPR2020)
[ICLR '26 Oral] Official repository of the paper "AnyUp: Universal Feature Upsampling".
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 …
DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)
🔥🔥🔥 Set the world of 3D faces on fire with INFERNO 🔥🔥🔥
MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]
Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision
Summary of publicly available ressources such as code, datasets, and scientific papers for the FLAME 3D head model
This is a implementation of the 3D FLAME model in PyTorch
68/21 Landmark points for Basel Face Model (3DMM)
Convert from Basel Face Model (BFM) to the FLAME head model
Official implementation for the SIGGRAPH Asia 2024 paper SPARK: Self-supervised Personalized Real-time Monocular Face Capture
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
Large Scale Facial Model (LSFM) - an automatic pipeline for constructing 3D Morphable Models from large collections of facial meshes
[ICME2025] From 2D Images to 3D Model: Weakly Supervised Multi-View Face Reconstruction with Deep Fusion
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.