Recent Progress of Face Image Synthesis
arXiv:1706.04717
Abstract
Face synthesis has been a fascinating yet challenging problem in computer vision and machine learning. Its main research effort is to design algorithms to generate photo-realistic face images via given semantic domain. It has been a crucial prepossessing step of main-stream face recognition approaches and an excellent test of AI ability to use complicated probability distributions. In this paper, we provide a comprehensive review of typical face synthesis works that involve traditional methods as well as advanced deep learning approaches. Particularly, Generative Adversarial Net (GAN) is highlighted to generate photo-realistic and identity preserving results. Furthermore, the public available databases and evaluation metrics are introduced in details. We end the review with discussing unsolved difficulties and promising directions for future research.
17 pages, 10 figures
References in corpus (8)
- Learning Face Representation from Scratch
- Energy-based Generative Adversarial Network
- Inverting face embeddings with convolutional neural networks
- GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
- Face Synthesis (FASY) System for Generation of a Face Image from Human Description
- Mask-off: Synthesizing Face Images in the Presence of Head-mounted Displays
- Example-Based Image Synthesis via Randomized Patch-Matching
- DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification