MVESF: Multi-View Enhanced Semantic Fusion for Controllable Text-to-Image Generation

Text-to-image(T2I) synthesis aims to generate semantically consistent images with texts. Currently, existing methods merely use the shallow semantics of the text to crudely guide image generation. They cannot fully integrate rich textual semantics with image features, leading to an inability to control image generation through text finely. To address this issue, we propose a GAN-based method named MVESF (Multi-View Enhanced Semantic Fusion), which enhances the semantic fusion of text and images from multiple perspectives for fine-grained controllable text-to-image synthesis. In multi-view, we introduce Multi-domain Semantic Guidance, Local Semantic Attention, and Visual-textual Consistency Loss to enhance the semantic fusion of text and images in image generation, image discrimination, and image supervision, respectively. Our method promotes the consistent alignment between text and images, allowing for fine-grained variations in the generated images when subtle changes in the input text without affecting unrelated regions. Extensive experimental results have demonstrated the effectiveness of our approach.