Efficient scene text image super-resolution with semantic guidance
ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2024)
摘要
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
更多查看译文
关键词
Scene text image super-resolution,efficient model,semantic guidance
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要