Enhanced Generative Structure Prior for Chinese Text Image Super-resolution

TL;DR

This paper presents a novel Chinese text image super-resolution framework that uses a structure prior within a StyleGAN model, effectively restoring detailed strokes of low-resolution characters with diverse styles and layouts.

Contribution

It introduces a structure prior integrated into StyleGAN with a codebook mechanism, specifically designed for Chinese characters, improving super-resolution quality over existing methods.

Findings

Robust restoration of detailed strokes in degraded Chinese characters.

Effective handling of diverse font styles and irregular layouts.

Superior performance demonstrated on real-world low-resolution Chinese text.

Abstract

Faithful text image super-resolution (SR) is challenging because each character has a unique structure and usually exhibits diverse font styles and layouts. While existing methods primarily focus on English text, less attention has been paid to more complex scripts like Chinese. In this paper, we introduce a high-quality text image SR framework designed to restore the precise strokes of low-resolution (LR) Chinese characters. Unlike methods that rely on character recognition priors to regularize the SR task, we propose a novel structure prior that offers structure-level guidance to enhance visual quality. Our framework incorporates this structure prior within a StyleGAN model, leveraging its generative capabilities for restoration. To maintain the integrity of character structures while accommodating various font styles and layouts, we implement a codebook-based mechanism that restricts the generative space of StyleGAN. Each code in the codebook represents the structure of a specific character, while the vector $w$ in StyleGAN controls the character's style, including typeface, orientation, and location. Through the collaborative interaction between the codebook and style, we generate a high-resolution structure prior that aligns with LR characters both spatially and structurally. Experiments demonstrate that this structure prior provides robust, character-specific guidance, enabling the accurate restoration of clear strokes in degraded characters, even for real-world LR Chinese text with irregular layouts. Our code and pre-trained models will be available at https://github.com/csxmli2016/MARCONetPlusPlus