Scene text image super-resolution (STISR), aiming to improve image quality while boosting downstream scene text recognition accuracy, has recently achieved great success. However, most existing methods treat the foreground (character regions) and background (non-character regions) equally in the forward process, and neglect the disturbance from the complex background, thus limiting the performance. To address these issues, in this paper, we propose a novel method LEMMA that explicitly models character regions to produce high-level text-specific guidance for super-resolution. To model the location of characters effectively, we propose the location enhancement module to extract character region features based on the attention map sequence. Besides, we propose the multi-modal alignment module to perform bidirectional visual-semantic alignment to generate high-quality prior guidance, which is then incorporated into the super-resolution branch in an adaptive manner using the proposed adaptive fusion module. Experiments on TextZoom and four scene text recognition benchmarks demonstrate the superiority of our method over other state-of-the-art methods. Code is available at https://github.com/csguoh/LEMMA.

翻译：场景文本图像超分辨率（Scene Text Image Super-Resolution, STISR）旨在提升图像质量的同时增强下游场景文本识别精度，近年来取得了显著成功。然而，现有多数方法在前向处理过程中对前景（字符区域）与背景（非字符区域）一视同仁，忽略了复杂背景的干扰，从而限制了性能。为解决这些问题，本文提出一种新颖方法LEMMA，通过显式建模字符区域生成高层文本特定指导信息用于超分辨率。为有效建模字符位置，我们提出位置增强模块，基于注意力图序列提取字符区域特征。此外，我们提出多模态对齐模块，执行双向视觉-语义对齐以生成高质量先验指导，并通过所提出的自适应融合模块以自适应方式将其融入超分辨率分支。在TextZoom及四个场景文本识别基准上的实验表明，本方法优于其他最先进方法。代码已开源至https://github.com/csguoh/LEMMA。