A collection for the face-related papers and codes.
Updated on 11/04/2017
- Multiview Face Detection: [Paper] [Code] (Caffe + Python)
- Finding Tiny Faces: [Project][Paper] [Code] (MatConvNet + MATLAB)
- Focal Loss: [Paper]
- SSH: [Paper]
- Face R-CNN: [Paper]
- FaceBoxes: [Paper] [Code] (Caffe)
- S3FD: [Paper]
In this part, you can retrieve the paper before 2016 on this site.
- PIFA: Pose-invariant 3D face alignment [Paper] [Code]
- MDM: Mnemonic Descent Method [Paper] [Code]
- JFA: Joint head pose estimation and face alignment [Paper]
- GoDP: Globally optimized dual path way [Paper]
- Recurrent 3D-2D Dual Learning: [Paper]
- UH-E2FAR [Paper]
- Multi-View RNN [Paper]
- 3D Face Morphable Models "In-the-Wild" [Paper]
- 3DMM-CNN [Paper] [Code]
- VRN [Paper] [Code]
- 3DFaceNet [Paper]
- MoFA: Unsupervised learning for 3D model and pose parameters [Paper]
- 3DMM-STN: Using 3DMM to transfer 2D image to 2D image texture [Paper]
- TP-GAN: [Paper]
- FF-GAN: [Paper]
- DR-GAN: [Paper] [Website]
- BEGAN: Boundary Equilibrium Generative Adversarial Networks [Paper]
- DeepFace: [Paper]
- DeepID series: [DeepID] [DeepID2] [DeepID3]
- VGG-Face: VGG-Face CNN descriptor.
- VGG-Face2: VGG-Face ResNet descriptor.
- Triplet Loss [Paper][Code](Torch) [Code](TensorFlow)
- Center Loss [Paper] [Code](Caffe + MATLAB) [Code] (MxNet)
- Range Loss [Paper] [Code] (Caffe)
- L-Softmax [Paper] [Code] (Caffe) [Code] (MxNet)
- A-Softmax Loss (SphereFace) [Paper] [Code] (Caffe)
- Marginal Loss [Paper]
- OpenFace: Face recognition with Google's FaceNet deep neural network using Torch.
- SeetaFaceEngine: An open source C++ face recognition engine.
- UR2D: 3D-aided 2D Face Recognition system
- Detection
- Recognition:
- MS-Celeb-1M: Microsoft dataset contains around 1M subjects [Paper] [Download]
- CASIA WebFace: 10,575 subjects and 494,414 images [Paper] [Download]
- LFW: 13,000 images and 5749 subjects [Download]
- CelebA: 202,599 images and 10,177 subjects, 5 landmark locations, 40 binary attributes [Download]
- MegaFace: 1 Million Faces for Recognition at Scale, 690,572 subjects [Download]
- VGG-Face2: A large-scale face dataset contains 3.31 million imaes of 9131 identities. [Download]
- Deep Learning:
- MXNet and Gluon: A flexible and efficient library for deep learning.
- Torch and PyTorch: Tensors and Dynamic neural networks in Python with strong GPU acceleration.
- TensorFlow: An open-source software library for Machine Intelligence.
- Caffe and Caffe2: A lightweight, modular, and scalable deep learning framework.
- Machine Learning:
- Dlib: A machine learning toolkit.
- Computer Vision:
- OpenCV: Open Source Computer Vision Library.
- Probabilistic Programming
- Pyro: Deep universal probabilistic programming with Python and PyTorch