Generating Image Sequence from Description with LSTM Conditional GAN
This addresses the problem of image generation from text for applications like content creation, but it appears incremental as it builds on existing GAN methods with a novel combination.
The paper tackled generating images from word descriptions by proposing an LSTM Conditional GAN architecture, trained on Oxford-102 Flowers and Caltech-UCSD Birds datasets, and demonstrated that it produces better results surpassing state-of-the-art approaches.
Generating images from word descriptions is a challenging task. Generative adversarial networks(GANs) are shown to be able to generate realistic images of real-life objects. In this paper, we propose a new neural network architecture of LSTM Conditional Generative Adversarial Networks to generate images of real-life objects. Our proposed model is trained on the Oxford-102 Flowers and Caltech-UCSD Birds-200-2011 datasets. We demonstrate that our proposed model produces the better results surpassing other state-of-art approaches.