Enhancing Text-To-Image Translation with Stack-Generative Adversarial Networks

Text-to-image translation is the process of generating visually coherent images from textual descriptions. Traditional GANs suffer from inadequacy in capturing intricate details and therefore pose an obstacle in achieving this task. Hence, in this paper, we propose an improved approach based on the concept of Stack Generative Adversarial Networks, in which the generative process is applied in two stages. Stage I produces a 64x64 low-resolution image that offers solid shapes and colors. Then, in Stage II, this is further intensified into a resolution of 256x256 such that it closely resembles the text input. The architecture of StackGAN surpasses the earlier variant GANs and other derivatives for it produces high-resolution images with semantic correctness closely following the description in the given text. The staged nature of this approach improves image quality while ensuring that a stronger relationship lies between the produced image and the input text. Future works will attempt to enhance the model's capabilities while applying it in other areas of synthesis in images.