ALR-GAN: Adaptive Layout Refinement for Text-to-Image Synthesis
This addresses layout misalignment issues in text-to-image generation for AI applications, but it is incremental as it builds on existing GAN-based methods.
The paper tackled the problem of improving layout alignment in text-to-image synthesis by proposing ALR-GAN, which adaptively refines object and background layouts without auxiliary information, achieving competitive performance on standard datasets.
We propose a novel Text-to-Image Generation Network, Adaptive Layout Refinement Generative Adversarial Network (ALR-GAN), to adaptively refine the layout of synthesized images without any auxiliary information. The ALR-GAN includes an Adaptive Layout Refinement (ALR) module and a Layout Visual Refinement (LVR) loss. The ALR module aligns the layout structure (which refers to locations of objects and background) of a synthesized image with that of its corresponding real image. In ALR module, we proposed an Adaptive Layout Refinement (ALR) loss to balance the matching of hard and easy features, for more efficient layout structure matching. Based on the refined layout structure, the LVR loss further refines the visual representation within the layout area. Experimental results on two widely-used datasets show that ALR-GAN performs competitively at the Text-to-Image generation task.