Image Generation from Caption
Image Generation from Caption Mahima Pandya and Sonal Rami Charotar University of Science and Technology, India ABSTRACT Generating images from a text description is as challenging as it is interesting. The Adversarial network performsinacompetitive fashion where the networks aretherivalry of each other. With the introduction ofGenerative Adversarial Network, lots of development is happening in the field of Computer Vision. Withgenerative adversarial networks as the baseline model, studied Stack GAN consisting oftwo-stageGANSstep-by- step in this paper that could be easily understood. This paper presents visual comparative study ofother models attempting to generate image conditioned on the text description. One sentencecan be relatedto many images. And to achieve this multi-modal characteristic, conditioning augmentation is also performed. The performance of Stack- GAN is better in generating images from captions due to its unique architecture. As it consists of two GANS inste...