face-reconstruction 话题在 GitHub 上没有填写简介，这里按 Star 数汇总最相关的热门仓库。
papers about Face Detection; Face Alignment; Face Recognition && Face Identification && Face Verification && Face Representation; Face Reconstruction; Face Tracking; Face Super-Resolution && Face Deblurring; Face Generation && Face Synthesis; Face Transfer; Face Anti-Spoofing; Face Retrieval;
学习在无 3D 监督下从图像回归 3D 人脸形状与表情
CVPR 2022 年论文《EMOCA：情感驱动单眼面部捕捉与动画》的官方仓库。EMOCA以一张面部图像为输入，生成三维重建。EMOCA树立了在真实中重建高度情感图像的新标准
一个从单目 RGB 图像进行高保真 3D 人脸重建的库
This is a implementation of the 3D FLAME model in PyTorch
极限3D面部重建：超越遮挡
一个使用 Pytorch 的 3DMM 拟合框架
[CVPR2023] A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Images.
FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset (CVPR2022)
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.
Facial Landmark Detection and head pose compute use dlib, Real time Face Reconstruction use 3D Morphable Face Model fitting
[ECCV 2020] Reimplementation of 3DDFAv2, including face mesh, head pose, landmarks, and more.
SPECTRE的官方Pytorch实现：通过视频进行视觉语音感知3D面部表情重建
A collection of face related papers
Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation (ECCV2022)
Powerful 3D passive liveness detection SDK accurately detecting face presentation attacks, including face printed photos, face cutout masks, face digital and video replay attacks, and face 3D masks.
[TIP 2021] SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction
面向快速现代研究的批量人脸处理，包括人脸检测、人脸对齐、人脸重建、头部姿态估计、人脸解析
3D human face estimation and rendering from a single image
This is the official repository for evaluation on the NoW Benchmark Dataset. The goal of the NoW benchmark is to introduce a standard evaluation metric to measure the accuracy and robustness of 3D face reconstruction methods from a single image under variations in viewing angle, lighting, and common occlusions.