UGAN: Untraceable GAN for Multi-Domain Face Translation
arXiv:1907.11418
Abstract
The multi-domain image-to-image translation is a challenging task where the goal is to translate an image into multiple different domains. The target-only characteristics are desired for translated images, while the source-only characteristics should be erased. However, recent methods often suffer from retaining the characteristics of the source domain, which are incompatible with the target domain. To address this issue, we propose a method called Untraceable GAN, which has a novel source classifier to differentiate which domain an image is translated from, and determines whether the translated image still retains the characteristics of the source domain. Furthermore, we take the prototype of the target domain as the guidance for the translator to effectively synthesize the target-only characteristics. The translator is learned to synthesize the target-only characteristics and make the source domain untraceable for the discriminator, so that the source-only characteristics are erased. Finally, extensive experiments on three face editing tasks, including face aging, makeup, and expression editing, show that the proposed UGAN can produce superior results over the state-of-the-art models. The source code will be released.
References in corpus (20)
- Conditional Generative Adversarial Nets
- Explaining and Harnessing Adversarial Examples
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Spectral Normalization for Generative Adversarial Networks
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Energy-based Generative Adversarial Network
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
- Invertible Conditional GANs for image editing
- The relativistic discriminator: a key element missing from standard GAN
- cGANs with Projection Discriminator
- DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
- Deep Identity-aware Transfer of Facial Attributes
- Loss-Sensitive Generative Adversarial Networks on Lipschitz Densities
- 3D-Aware Scene Manipulation via Inverse Graphics
- Cross-domain Human Parsing via Adversarial Feature and Label Adaptation