Context-Aware Unsupervised Text Stylization

Shuai Yang, Jiaying Liu, Wenhan Yang, Zongming Guo

Abstract: In this work, we present a novel algorithm to stylize the text without supervision, which provides a flexible and convenient way to invoke fantastic text expressions. Rather than employing the fixed pair of target text and source style images, our unsupervised framework establishes an implicit mapping for them by using an abstract imagery of the style image as bridges. Based on the mapping, we progressively narrow the visual discrepancy between text and style images by the proposed legibility-preserving structure transfer and texture transfer algorithms, which effectively balance the text legibility and style consistency. Furthermore, we explore a seamless composition of the stylized text and a background image, in which the optimal text layout is determined by a context-aware layout design algorithm utilizing cues for both seamlessness and aesthetics. Given the layout, the text can be seamlessly embedded into the background by texture synthesis under a context-aware boundary constraint. Experimental results demonstrate the superiority of the proposed method for automatic artistic typography creation over state-of-the-art style transfer methods. In addition, we validate the effectiveness of our algorithm with extensive experiments on various tasks, such as visual-textual presentation synthesis and symbol rendering.