用OCR信息辅助压缩，让小字文本更清晰不损整体画质
TextBoost: Boosting Scene Text Fidelity in Ultra-low Bitrate Image Compression
- 用OCR提取文本信息做解码引导，无额外传输开销
- 在低比特率下文本识别F1提升60.6%，PSNR和bpp相当
- 适合需要高保真文字的图像压缩场景，如证件、广告
超低比特率图像压缩面临核心挑战：在保持整体视觉质量的同时保留小字号场景文本。传统感兴趣区域（ROI）比特分配虽可优先保护文本，但常损害全局保真度，导致局部准确与整体质量间的权衡。本文提出不依赖ROI编码的新方法——通过轻量级OCR提取辅助文本信息并以极低开销传输，使解码器可利用语义指引进行重建。TextBoost采用三项关键设计：(i) 自适应过滤OCR输出并生成引导图；(ii) 通过注意力融合模块将引导信息与解码特征校准结合；(iii) 在文本区域引入一致性正则化损失，促进自然融合。在TextOCR与ICDAR 2015数据集上的大量实验表明，该方法在相近峰值信噪比（PSNR）和比特每像素（bpp）条件下，文本识别F1最高提升60.6%，实现小字文本更清晰、全局质量不下降，并有效解耦文本增强与全局率失真优化。
原文摘要 · Abstract (English)
Ultra-low bitrate image compression faces a critical challenge: preserving small-font scene text while maintaining overall visual quality. Region-of-interest (ROI) bit allocation can prioritize text but often degrades global fidelity, leading to a trade-off between local accuracy and overall image quality. Instead of relying on ROI coding, we incorporate auxiliary textual information extracted by OCR and transmitted with negligible overhead, enabling the decoder to leverage this semantic guidance. Our method, TextBoost, operationalizes this idea through three strategic designs: (i) adaptively filtering OCR outputs and rendering them into a guidance map; (ii) integrating this guidance with decoder features in a calibrated manner via an attention-guided fusion block; and (iii) enforcing guidance-consistent reconstruction in text regions with a regularizing loss that promotes natural blending with the scene. Extensive experiments on TextOCR and ICDAR 2015 demonstrate that TextBoost yields up to 60.6% higher text-recognition F1 at comparable Peak Signal-to-Noise Ratio (PSNR) and bits per pixel (bpp), producing sharper small-font text while preserving global image quality and effectively decoupling text enhancement from global rate-distortion optimization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。