HelloFace：人脸资源精选（代表性工作、最新研究、论文、代码等，Updating）

加入极市专业CV交流群，与6000+来自腾讯，华为，百度，北大，清华，中科院等名企名校视觉开发者互动交流！更有机会与李开复老师等大牛群内互动！

同时提供每月大咖直播分享、真实项目需求对接、干货资讯汇总，行业技术交流。扫描文末二维码立刻申请入群~

分享一个超全的人脸算法资源，是从之前传统方法到现在深度学习方法比较有代表性、实用性、或者最新研究的一份列表，其中也包括了项目、数据集、论文、代码，一些常用的库和工具等，强烈推荐！

作者：becauseofAI
项目地址：

https://github.com/becauseofAI/HelloFace
该项目还在持续更新中，欢迎点star以资鼓励，更欢迎通过issue的方式或者pull request一起贡献~

注：本文涉及较多超链接，请点击文末阅读原文，以获得更好的阅读体验。

HelloFace 

Face Technology Repository(Updating)

👋Recent Update

2019/01/12

• 2018Survey: Deep Facial Expression Recognition: A Survey

• 2018Survey: Deep Face Recognition: A Survey

• SphereFace+(MHE): Learning towards Minimum Hyperspherical Energy

• HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

2018/12/01

• FRVT: Face Recognition Vendor Test

• GANimation: Anatomically-aware Facial Animation from a Single Image

• StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation

• Faceswap: A tool that utilizes deep learning to recognize and swap faces in pictures and videos

• HF-PIM: Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization

• PRNet: Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

• LAB: Look at Boundary: A Boundary-Aware Face Alignment Algorithm

• Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs

• Face-Alignment: How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)

• Face3D: Python tools for processing 3D face

• IMDb-Face: The Devil of Face Recognition is in the Noise

• AAM-Softmax(CCL): Face Recognition via Centralized Coordinate Learning

• AM-Softmax: Additive Margin Softmax for Face Verification

• FeatureIncay: Feature Incay for Representation Regularization

• NormFace: L2 hypersphere embedding for face Verification

• CocoLoss: Rethinking Feature Discrimination and Polymerization for Large-scale Recognition

• L-Softmax: Large-Margin Softmax Loss for Convolutional Neural Networks

2018/07/21

• MobileFace: A face recognition solution on mobile device

• Trillion Pairs: Challenge 3: Face Feature Test/Trillion Pairs

• MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices

2018/04/20

• PyramidBox: A Context-assisted Single Shot Face Detector

• PCN: Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks

• S³FD: Single Shot Scale-invariant Face Detector

• SSH: Single Stage Headless Face Detector

• NPD: A Fast and Accurate Unconstrained Face Detector

• PICO: Object Detection with Pixel Intensity Comparisons Organized in Decision Trees

• libfacedetection: A fast binary library for face detection and face landmark detection in images.

• SeetaFaceEngine: SeetaFace Detection, SeetaFace Alignment and SeetaFace Identification.

• FaceID: An implementation of iPhone X's FaceID using face embeddings and siamese networks on RGBD images.

2018/03/28

• InsightFace(ArcFace): 2D and 3D Face Analysis Project

• CosFace: Large Margin Cosine Loss for Deep Face Recognition

🔖Face Benchmark and Dataset

Face Recognition

• FRVT: Face Recognition Vendor Test [project] [leaderboard]

• IMDb-Face: The Devil of Face Recognition is in the Noise(59k people in 1.7M images) [paper] [dataset]

• Trillion Pairs: Challenge 3: Face Feature Test/Trillion Pairs(MS-Celeb-1M-v1c with 86,876 ids/3,923,399 aligned images + Asian-Celeb 93,979 ids/2,830,146 aligned images) [benckmark] [dataset] [result]

• MF2: Level Playing Field for Million Scale Face Recognition(672K people in 4.7M images) [paper] [dataset] [result][benckmark]

• MegaFace: The MegaFace Benchmark: 1 Million Faces for Recognition at Scale(690k people in 1M images) [paper][dataset] [result] [benckmark]

• UMDFaces: An Annotated Face Dataset for Training Deep Networks(8k people in 367k images with pose, 21 key-points and gender) [paper] [dataset]

• MS-Celeb-1M: A Dataset and Benchmark for Large Scale Face Recognition(100K people in 10M images) [paper] [dataset][result] [benchmark] [project]

• VGGFace2: A dataset for recognising faces across pose and age(9k people in 3.3M images) [paper] [dataset]

• VGGFace: Deep Face Recognition(2.6k people in 2.6M images) [paper] [dataset]

• CASIA-WebFace: Learning Face Representation from Scratch(10k people in 500k images) [paper] [dataset]

• LFW: Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments(5.7k people in 13k images) [report] [dataset] [result] [benchmark]

Face Detection

• WiderFace: WIDER FACE: A Face Detection Benchmark(400k people in 32k images with a high degree of variability in scale, pose and occlusion) [paper] [dataset] [result] [benchmark]

• FDDB: A Benchmark for Face Detection in Unconstrained Settings(5k faces in 2.8k images) [report] [dataset] [result][benchmark]

Face Landmark

• LS3D-W: A large-scale 3D face alignment dataset constructed by annotating the images from AFLW, 300VW, 300W and FDDB in a consistent manner with 68 points using the automatic method [paper] [dataset]

• AFLW: Annotated Facial Landmarks in the Wild: A Large-scale, Real-world Database for Facial Landmark Localization(25k faces with 21 landmarks) [paper] [benchmark]

Face Attribute

• CelebA: Deep Learning Face Attributes in the Wild(10k people in 202k images with 5 landmarks and 40 binary attributes per image) [paper] [dataset]

🔖Face Recognition

• 2018Survey: Deep Facial Expression Recognition: A Survey [paper]

• 2018Survey: Deep Face Recognition: A Survey [paper]

• SphereFace+(MHE): Learning towards Minimum Hyperspherical Energy [paper] [code]

• MobileFace: A face recognition solution on mobile device [code]

• MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices [paper] [code1] [code2][code3] [code4]

• FaceID: An implementation of iPhone X's FaceID using face embeddings and siamese networks on RGBD images. [code][blog]

• InsightFace(ArcFace): 2D and 3D Face Analysis Project [paper] [code1] [code2]

• AAM-Softmax(CCL): Face Recognition via Centralized Coordinate Learning [paper]

• AM-Softmax: Additive Margin Softmax for Face Verification [paper] [code1] [code2]

• CosFace: Large Margin Cosine Loss for Deep Face Recognition [paper] [code1] [code2]

• FeatureIncay: Feature Incay for Representation Regularization [paper]

• CocoLoss: Rethinking Feature Discrimination and Polymerization for Large-scale Recognition [paper] [code]

• NormFace: L2 hypersphere embedding for face Verification [paper] [code]

• SphereFace(A-Softmax): Deep Hypersphere Embedding for Face Recognition [paper] [code]

• L-Softmax: Large-Margin Softmax Loss for Convolutional Neural Networks [paper] [code1] [code2] [code3] [code4][code5] [code6] [code7]

• CenterLoss: A Discriminative Feature Learning Approach for Deep Face Recognition [paper] [code1] [code2] [code3][code4]

• OpenFace: A general-purpose face recognition library with mobile applications [report] [project] [code1] [code2]

• FaceNet: A Unified Embedding for Face Recognition and Clustering [paper] [code]

• DeepID3: DeepID3: Face Recognition with Very Deep Neural Networks [paper]

• DeepID2+: Deeply learned face representations are sparse, selective, and robust [paper]

• DeepID2: Deep Learning Face Representation by Joint Identification-Verification [paper]

• DeepID: Deep Learning Face Representation from Predicting 10,000 Classes [paper]

• DeepFace: Closing the gap to human-level performance in face verification [paper]

• LBP+Joint Bayes: Bayesian Face Revisited: A Joint Formulation [paper] [code1] [code2] [code3]

• LBPFace: Face recognition with local binary patterns [paper] [code]

• FisherFace(LDA): Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection [paper] [code]

• EigenFace(PCA): Face recognition using eigenfaces [paper] [code]

🔖Face Detection

• HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition [paper] [code]

• PyramidBox: A Context-assisted Single Shot Face Detector [paper] [code]

• PCN: Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks [paper] [code]

• S³FD: Single Shot Scale-invariant Face Detector [paper] [code]

• SSH: Single Stage Headless Face Detector [paper] [code]

• FaceBoxes: A CPU Real-time Face Detector with High Accuracy [paper][code1] [code2]

• TinyFace: Finding Tiny Faces [paper] [project] [code1] [code2] [code3]

• MTCNN: Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks [paper] [project][code1] [code2] [code3] [code4] [code5] [code6] [code7]

• NPD: A Fast and Accurate Unconstrained Face Detector [paper] [code] [project]

• PICO: Object Detection with Pixel Intensity Comparisons Organized in Decision Trees [paper] [code]

• libfacedetection: A fast binary library for face detection and face landmark detection in images. [code]

• SeetaFaceEngine: SeetaFace Detection, SeetaFace Alignment and SeetaFace Identification [code]

🔖Face Landmark

• PRNet: Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network [paper] [code]

• LAB: Look at Boundary: A Boundary-Aware Face Alignment Algorithm [paper] [project] [code]

• Face-Alignment: How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks) [paper] [project] [code1] [code2]

• ERT: One Millisecond Face Alignment with an Ensemble of Regression Trees [paper] [code]

🔖Face GAN

• HF-PIM: Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization [paper]

• Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs [paper]

• GANimation: Anatomically-aware Facial Animation from a Single Image [paper] [project] [code]

• StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation [paper] [code]

• PGAN: Progressive Growing of GANs for Improved Quality, Stability, and Variation [paper] [code1] [code2]

• Faceswap: A tool that utilizes deep learning to recognize and swap faces in pictures and videos [code1] [code2]

Face Lib&Tool

• Dlib [url] [github]

• OpenCV [docs] [github]

• Face3D [github]

*延伸阅读

---

点击左下角“阅读原文”，即可申请加入极市目标跟踪、目标检测、工业检测、人脸方向、视觉竞赛等技术交流群，更有每月大咖直播分享、真实项目需求对接、干货资讯汇总，行业技术交流，一起来让思想之光照的更远吧~

觉得有用麻烦给个好看啦~