1. MRP-GAN: Multi-resolution parallel generative adversarial networks for text-to-image synthesis
- Author
-
Shu Zhan, Xinke Li, Liangfeng Xu, Zhongjian Qi, and Chaogang Fan
- Subjects
Structure (mathematical logic) ,Computer science ,business.industry ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Process (computing) ,Pattern recognition ,02 engineering and technology ,Residual ,Semantics ,01 natural sciences ,Image (mathematics) ,Image synthesis ,Artificial Intelligence ,Multi resolution ,0103 physical sciences ,Signal Processing ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Computer Vision and Pattern Recognition ,Artificial intelligence ,010306 general physics ,business ,Software ,Generative grammar - Abstract
Synthesizing photographic images from given text descriptions is a challenging problem. Although current methods first synthesize an initial blurred image, then refine the initial image to a high-quality one, the most existing methods are difficult to refine the initial image to an image corresponding to the text description. In this paper, the Multi-resolution Parallel Generative Adversarial Networks for Text-to-Image Synthesis (MRP-GAN) is proposed to generate photographic images. MRP-GAN introduces a Multi-resolution Parallel structure to refine the initial images when the initial images are not synthesized well. The low-resolution semantics are maintained through the whole process by Multi-resolution Parallel structure. Response Gate is designed to fully explore the capability of Multi-resolution Parallel structure by aggregating the outputs of the multi-resolution parallel subnetworks. We also utilize an attention mechanism, named Residual Attention Network, to fine-tune more fine-grained details of the generated images. We evaluate our MRP-GAN model on the CUB and MS-COCO datasets. Extensive experiments demonstrate the state-of-the-art performance of MRP-GAN. Besides, we apply a Multi-resolution Parallel structure in the existing method to verify its transferability.
- Published
- 2021
- Full Text
- View/download PDF