Understanding Text to Image Generation Techniques

Authors

  • Apoorv Khanduri
  • Piyush Kumar
  • Ashish Joshi
  • Rahul Kumar

Abstract

In recent years, Generative Adversarial Networks (GANs) have been successful in generating realistic looking detailed images and has applications in data augmentation, astronomy, photo editing. This survey gives a brief introduction and review’s recent improvement in Generative Adversarial Networks (GAN’s) to generate images from their text descriptions. We present their effectiveness, their improvement and further scope of research and discussion on this topic. Introduction: text to image generation is the process of generating images from any set of data based on their text descriptions. The text description forms a part of the model which guides the model to create the image. Text to image generation forms a part of descriptive designing and multimodal learning and drives research for simplification and idea generation based on text description. Text to image generation solves the core problem of creating computer aided design by simple text description. Thus, all T2I problems encompass a GAN which is conditioned on text and thus unlike VanillaGAN or DCGAN will generate image based on the condition which is given to it. Why is t2i optimal for text to image? The improvement in GAN are towards global and local images to improve clarity of different parts of image and is also geared towards better semantic meaning of the given input.

Keywords: image generation techniques, GAN, T2I, text description, semantic technology

Cite this Article: Apoorv Khanduri, Piyush Kumar, Ashish Joshi, Rahul Kumar. Understanding Text to Image Generation Techniques. Journal of Software Engineering Tools & Technology Trends. 2020; 7(1): 18–24p.

Downloads

Published

2020-06-02

Issue

Vol. 7 No. 1 (2020)

Section

Research Articles

License

Declaration and Copyright Transfer Form

(to be completed by authors)

I/ We, the undersigned author(s) of the submitted manuscript, hereby declare, that the above manuscript which is submitted for publication in the STM Journals(s), is not published already in part or whole (except in the form of abstract) in any journal or magazine for private or public circulation, and, is not under consideration of publication elsewhere.

  • I/We will not withdraw the manuscript after 1 week of submission as I have read the Author Guidelines and will adhere to the guidelines.
  • I/We Author(s ) have niether given nor will give this manuscript elsewhere for publishing after submitting in STM Journal(s).
  • I/ We have read the original version of the manuscript and am/ are responsible for the thought contents embodied in it. The work dealt in the manuscript is my/ our own, and my/ our individual contribution to this work is significant enough to qualify for authorship.
  •  I/We also agree to the authorship of the article in the following order:

Author’s name                                    

 

1. ________________

2. ________________

3. ________________

4. ________________

 

We  Author(s) tick this box and would request you to consider it as our signature as we agree to the terms of this Copyright Notice, which will apply to this submission if and when it is published by this journal.