UGAN: Untraceable GAN for Multi-Domain Face Translation
This work addresses the challenge of producing target-only images in multi-domain face editing, which is important for applications like digital media and security, though it is incremental as it builds on existing GAN-based translation methods.
The paper tackles the problem of multi-domain face translation where existing methods often retain incompatible source domain characteristics, and proposes UGAN which uses a source classifier and target prototypes to erase source-only traits, achieving superior results in face aging, makeup, and expression editing tasks.
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.