Segmentation Guided Image-to-Image Translation with Adversarial Networks
This work addresses image quality and spatial controllability issues in image-to-image translation, which is important for applications like computer vision and graphics, but it appears incremental as it builds on existing GAN methods.
The paper tackles the problem of unrealistic and low-quality images in image-to-image translation by proposing a segmentation-guided GAN that uses semantic information to improve generation and spatial control. Experimental results on face image translation show superiority in image quality over state-of-the-art methods.
Recently image-to-image translation has received increasing attention, which aims to map images in one domain to another specific one. Existing methods mainly solve this task via a deep generative model, and focus on exploring the relationship between different domains. However, these methods neglect to utilize higher-level and instance-specific information to guide the training process, leading to a great deal of unrealistic generated images of low quality. Existing methods also lack of spatial controllability during translation. To address these challenge, we propose a novel Segmentation Guided Generative Adversarial Networks (SGGAN), which leverages semantic segmentation to further boost the generation performance and provide spatial mapping. In particular, a segmentor network is designed to impose semantic information on the generated images. Experimental results on multi-domain face image translation task empirically demonstrate our ability of the spatial modification and our superiority in image quality over several state-of-the-art methods.