Context-Aware Text-Based Binary Image Stylization and Synthesis

TL;DR

This paper introduces a novel framework for stylizing text-based binary images by transferring style while preserving legibility, and seamlessly embedding them into backgrounds with context-aware layout and texture synthesis.

Contribution

The work presents a new structure and texture transfer algorithm for binary images, combined with a context-aware layout and embedding method, advancing automatic artistic typography and related applications.

Findings

Outperforms state-of-the-art style transfer methods in artistic typography.

Effective in various tasks like icon rendering and image inpainting.

Capable of unsupervised text stylization with high visual quality.

Abstract

In this work, we present a new framework for the stylization of text-based binary images. First, our method stylizes the stroke-based geometric shape like text, symbols and icons in the target binary image based on an input style image. Second, the composition of the stylized geometric shape and a background image is explored. To accomplish the task, we propose legibility-preserving structure and texture transfer algorithms, which progressively narrow the visual differences between the binary image and the style image. The stylization is then followed by a context-aware layout design algorithm, where cues for both seamlessness and aesthetics are employed to determine the optimal layout of the shape in the background. Given the layout, the binary image is seamlessly embedded into the background by texture synthesis under a context-aware boundary constraint. According to the contents of binary images, our method can be applied to many fields. We show that the proposed method is capable of addressing the unsupervised text stylization problem and is superior to state-of-the-art style transfer methods in automatic artistic typography creation. Besides, extensive experiments on various tasks, such as visual-textual presentation synthesis, icon/symbol rendering and structure-guided image inpainting, demonstrate the effectiveness of the proposed method.