# Face rotation/Photorealistic Frontal View synthesis
## GAN
- [Unsupervised Depth Estimation, 3D Face Rotation and Replacement](https://arxiv.org/pdf/1803.09202v5.pdf),
[code](https://github.com/joelmoniz/DepthNets)
+ Present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image. DepthNets, can therefore be used to infer plausible 3D transformations from one face pose to another, allowing faces to be frontalized, transformed into 3D models or even warped to another pose and facial geometry.

- [Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis](http://openaccess.thecvf.com/content_ICCV_2017/papers/Huang_Beyond_Face_Rotation_ICCV_2017_paper.pdf),
[code](https://github.com/HRLTY/TP-GAN)
+ Proposes a Two-Pathway Generative Adversarial Network (TP-GAN) for photorealistic frontal view synthesis by simultaneously perceiving global structures and local details.
- [Pose-Guided Photorealistic Face Rotation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hu_Pose-Guided_Photorealistic_Face_CVPR_2018_paper.pdf)
+ Propose a novel Couple-Agent Pose-Guided Generative Adversarial Network (CAPG-GAN) to generate both neutral and profile.
head pose face images.
- [Unsupervised Face Normalization with Extreme Pose and Expression in the Wild (CVPR2019)](http://openaccess.thecvf.com/content_CVPR_2019/papers/Qian_Unsupervised_Face_Normalization_With_Extreme_Pose_and_Expression_in_the_CVPR_2019_paper.pdf),[code](https://github.com/mx54039q/fnm)
+ Propose a Face Normalization Model (FNM) to generate a frontal, neutral expression, photorealistic face image for face recognition.

## 3D Rendering
- [Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network](https://arxiv.org/pdf/1612.04904v1.pdf),[code](https://github.com/anhttran/3dmm_cnn)

- [Extreme 3D Face Reconstruction: Seeing Through Occlusions](https://arxiv.org/pdf/1712.05083v2.pdf), [code](https://github.com/anhttran/extreme_3d_faces)
+ Existing single view, 3D face reconstruction methods can produce beautifully detailed 3D results, but typically only for near frontal, unobstructed viewpoints. Showing how a deep convolutional encoder-decoder can be used to estimate such bump maps.

- [Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network](https://arxiv.org/pdf/1803.07835v1.pdf), [code](https://github.com/YadiraF/PRNet)
+ Propose an end-to-end method called Position map Regression Network (PRN) to jointly predict dense alignment and reconstruct 3D face shape.
+ The main features are:
End-to-End our method can directly regress the 3D facial structure and dense alignment from a single image bypassing 3DMM fitting.
Multi-task By regressing position map, the 3D geometry along with semantic meaning can be obtained. Thus, we can effortlessly complete the tasks of dense alignment, monocular 3D face reconstruction, pose estimation, etc.
Faster than real-time The method can run at over 100fps(with GTX 1080) to regress a position map.
Robust Tested on facial images in unconstrained conditions. Our method is robust to poses, illuminations and occlusions.
- [Improving Face Anti-Spoofing by 3D Virtual Synthesis](https://arxiv.org/pdf/1901.00488v2.pdf), [code](https://github.com/cleardusk/3DDFA) - 8 Apr 2019
+ A method to synthesize virtual spoof data in 3D space to alleviate this problem. The results open up new possibilities for advancing face anti-spoofing using cheap and largescale synthetic data.