Fine-grained Semantic Constraint in Image Synthesis
This addresses the challenge of precise semantic control in image synthesis for computer vision applications, representing an incremental improvement over existing GAN methods.
The paper tackles the problem of controlling image generation with fine-grained semantic constraints, proposing a multi-stage high-resolution model that uses attributes and masks as input to reduce unexpected diversity in GAN outputs while improving realism.
In this paper, we propose a multi-stage and high-resolution model for image synthesis that uses fine-grained attributes and masks as input. With a fine-grained attribute, the proposed model can detailedly constrain the features of the generated image through rich and fine-grained semantic information in the attribute. With mask as prior, the model in this paper is constrained so that the generated images conform to visual senses, which will reduce the unexpected diversity of samples generated from the generative adversarial network. This paper also proposes a scheme to improve the discriminator of the generative adversarial network by simultaneously discriminating the total image and sub-regions of the image. In addition, we propose a method for optimizing the labeled attribute in datasets, which reduces the manual labeling noise. Extensive quantitative results show that our image synthesis model generates more realistic images.