Gradient-Based Graph Attention for Scene Text Image Super-resolution

Scene text image super-resolution (STISR) in the wild has been shown to be beneficial to support improved vision-based text recognition from low-resolution imagery. An intuitive way to enhance STISR performance is to explore the well-structured and repetitive layout characteristics of text and exploit these as prior knowledge to guide model convergence. In this paper, we propose a novel gradient-based graph attention method to embed patch-wise text layout contexts into image feature representations for high-resolution text image reconstruction in an implicit and elegant manner. We introduce a non-local group-wise attention module to extract text features which are then enhanced by a cascaded channel attention module and a novel gradient-based graph attention module in order to obtain more effective representations by exploring correlations of regional and local patch-wise text layout properties. Extensive experiments on the benchmark TextZoom dataset convincingly demonstrate that our method supports excellent text recognition and outperforms the current state-of-the-art in STISR. The source code is available at https://github.com/xyzhu1/TSAN.

Authors

• Xiangyuan Zhu School of Computer Science and Engineering, Central South University
• Kehua Guo School of Computer Science and Engineering, Central South University
• Hui Fang Shanghai University of Finance and Economics
• Rui Ding Microsoft
• Zheng Wu School of Computer Science and Engineering, Central South University
• Gerald Schaefer Department of Computer Science, Loughborough University, U.K.

Keywords

• CV: Applications
• CV: Image and Video Retrieval
• CV: Interpretability and Transparency
• CV: Language and Vision
• CV: Learning & Optimization for CV
• CV: Low Level & Physics-based Vision