Semantically-aware Mask CycleGAN for Translating Artistic Portraits to Photo-realistic Visualizations
This work addresses a domain-specific gap in image-to-image translation for artistic portraits, offering a tailored solution for applications like digital art restoration or photo-realistic rendering.
The authors tackled the problem of translating artistic portraits to photo-realistic images by proposing the Semantic-aware Mask CycleGAN (SMCycleGAN), which uses semantically masked fake samples to improve realism while minimizing content loss, resulting in significantly increased realism in generated images.
Image-to-image translation (I2I) is defined as a computer vision task where the aim is to transfer images in a source domain to a target domain with minimal loss or alteration of the content representations. Major progress has been made since I2I was proposed with the invention of a variety of revolutionary generative models. Among them, GAN-based models perform exceptionally well as they are mostly tailor-made for specific domains or tasks. However, few works proposed a tailor-made method for the artistic domain. In this project, I propose the Semantic-aware Mask CycleGAN (SMCycleGAN) architecture which can translate artistic portraits to photo-realistic visualizations. This model can generate realistic human portraits by feeding the discriminators semantically masked fake samples, thus enforcing them to make discriminative decisions with partial information so that the generators can be optimized to synthesize more realistic human portraits instead of increasing the similarity of other irrelevant components, such as the background. Experiments have shown that the SMCycleGAN generate images with significantly increased realism and minimal loss of content representations.