GAN-Based Facial Attractiveness Enhancement
arXiv:2006.02766
Abstract
We propose a generative framework based on generative adversarial network (GAN) to enhance facial attractiveness while preserving facial identity and high-fidelity. Given a portrait image as input, having applied gradient descent to recover a latent vector that this generative framework can use to synthesize an image resemble to the input image, beauty semantic editing manipulation on the corresponding recovered latent vector based on InterFaceGAN enables this framework to achieve facial image beautification. This paper compared our system with Beholder-GAN and our proposed result-enhanced version of Beholder-GAN. It turns out that our framework obtained state-of-art attractiveness enhancement results. The code is available at https://github.com/zoezhou1999/BeautifyBasedOnGAN.
References in corpus (13)
- Conditional Generative Adversarial Nets
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
- Invertible Conditional GANs for image editing
- Unsupervised Image-to-Image Translation Networks
- Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
- Precise Recovery of Latent Vectors from Generative Adversarial Networks
- Interpreting the Latent Space of GANs for Semantic Face Editing
- A new humanlike facial attractiveness predictor with cascaded fine-tuning deep learning model
- Class-Splitting Generative Adversarial Networks
- SCUT-FBP5500: A Diverse Benchmark Dataset for Multi-Paradigm Facial Beauty Prediction
- Transferring Rich Deep Features for Facial Beauty Prediction
- Understanding Beauty via Deep Facial Features