High-Resolution Realistic Image Synthesis from Text Using Iterative Generative Adversarial Network

Synthesizing high-resolution realistic images from text description using one iteration Generative Adversarial Network (GAN) is difficult without using any additional techniques because mostly the blurry artifacts and mode collapse problems are occurring. To reduce these problems, this paper proposes an Iterative Generative Adversarial Network (iGAN) which takes three iterations to synthesize highresolution realistic image from their text description. In the 1st iteration, GAN synthesizes a low-resolution 64 x 64 pixels basic shape and basic color image from the text description with less mode collapse and blurry artifacts problems. In the 2nd iteration, GAN takes the result of the 1st iteration and text description again and synthesizes a better resolution 128 x 128 pixels better shape and well color image with very less mode collapse and blurry artifacts problems. In the last iteration, GAN takes the result of the 2nd iteration and text description as well and synthesizes a high-resolution 256x256 well shape and clear image with almost no mode collapse and blurry artifacts problems. Our proposed iGAN shows a significant performance on CUB birds and Oxford-102 flowers datasets. Moreover, iGAN improves the inception score and human rank as compare to the other state-of-the-art methods.