Efficient scene text image super-resolution with semantic guidance
This work addresses the need for efficient super-resolution methods for deployment on resource-limited platforms, offering an incremental improvement over existing approaches.
The paper tackles the problem of inefficient scene text image super-resolution by proposing SGENet, a lightweight framework that uses semantic guidance to enhance text understanding, achieving excellent performance with fewer computational costs.
Scene text image super-resolution has significantly improved the accuracy of scene text recognition. However, many existing methods emphasize performance over efficiency and ignore the practical need for lightweight solutions in deployment scenarios. Faced with the issues, our work proposes an efficient framework called SGENet to facilitate deployment on resource-limited platforms. SGENet contains two branches: super-resolution branch and semantic guidance branch. We apply a lightweight pre-trained recognizer as a semantic extractor to enhance the understanding of text information. Meanwhile, we design the visual-semantic alignment module to achieve bidirectional alignment between image features and semantics, resulting in the generation of highquality prior guidance. We conduct extensive experiments on benchmark dataset, and the proposed SGENet achieves excellent performance with fewer computational costs. Code is available at https://github.com/SijieLiu518/SGENet