Parametric Synthesis of Text on Stylized Backgrounds using PGGANs

2018/09/22 by Mayank Gupta, Abhinav Kumar, Gupta, Mayank +3
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Handwritten Text Recognition Techniques #Image Processing and 3D Reconstruction

paper · pdf · doi:10.48550/arxiv.1809.08488

openalex publication_date 2018/09/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We describe a novel method of generating high-resolution real-world images of text where the style and textual content of the images are described parametrically. Our method combines text to image retrieval techniques with progressive growing of Generative Adversarial Networks (PGGANs) to achieve conditional generation of photo-realistic images that reflect specific styles, as well as artifacts seen in real-world images. We demonstrate our method in the context of automotive license plates. We assess the impact of varying the number of training images of each style on the fidelity of the generated style, and demonstrate the quality of the generated images using license plate recognition systems.

Citations

• Improved Training of Wasserstein GANs
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

Related

• StackGAN: Text to Photo-realistic Image Synthesis with Stacked\n Generative Adversarial Networks
• Style Generation: Image Synthesis based on Coarsely Matched Texts
• Generative Adversarial Text to Image Synthesis
• StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
• Text-To-Image with Generative Adversarial Networks