GlyphPrinter：面向字形精确视觉文本渲染的区域分组直接偏好优化
GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering
将 DPO 从整体偏好扩展到区域级偏好，并引入区域奖励引导的推理采样策略，为视觉文本渲染中的局部字形错误提供可复用的偏好优化框架。
原文依据 we construct the GlyphCorrector dataset with region-level glyph preference annotations and propose Region-Grouped DPO
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论生成准确的字形对于视觉文本渲染至关重要，但仍具挑战性。现有方法通常通过在大量高质量场景文本图像上训练来增强文本渲染，但字形变化覆盖有限且过度风格化往往损害字形准确性，尤其是对复杂或域外字符。一些方法利用强化学习缓解该问题，但其奖励模型通常依赖对细粒度字形错误不敏感的文本识别系统，因此字形错误的图像仍可能获得高奖励。受直接偏好优化（DPO）启发，我们提出 GlyphPrinter，一种基于偏好的文本渲染方法，消除了对显式奖励模型的依赖。然而，标准 DPO 目标仅建模两个样本间的整体偏好，这对于字形错误通常发生在局部区域的视觉文本渲染而言是不够的。为解决该问题，我们构建了具有区域级字形偏好标注的 GlyphCorrector 数据集，并提出区域分组 DPO（R-GDPO），一种基于区域的目标，优化标注区域上的样本间和样本内偏好，显著提升字形准确性。此外，我们引入区域奖励引导，一种从具有可控字形准确性的最优分布中采样的推理策略。大量实验表明，所提出的 GlyphPrinter 在字形准确性上优于现有方法，同时在风格化与精确性之间保持良好平衡。
英文原文摘要 1622 字符
Generating accurate glyphs for visual text rendering is essential yet challenging. Existing methods typically enhance text rendering by training on a large amount of high-quality scene text images, but the limited coverage of glyph variations and excessive stylization often compromise glyph accuracy, especially for complex or out-of-domain characters. Some methods leverage reinforcement learning to alleviate this issue, yet their reward models usually depend on text recognition systems that are insensitive to fine-grained glyph errors, so images with incorrect glyphs may still receive high rewards. Inspired by Direct Preference Optimization (DPO), we propose ***GlyphPrinter***, a preference-based text rendering method that eliminates reliance on explicit reward models. However, the standard DPO objective only models overall preference between two samples, which is insufficient for visual text rendering where glyph errors typically occur in localized regions. To address this issue, we construct the ***GlyphCorrector*** dataset with region-level glyph preference annotations and propose ***Region-Grouped DPO*** (***R-GDPO***), a region-based objective that optimizes inter- and intra-sample preferences over annotated regions, substantially enhancing glyph accuracy. Furthermore, we introduce ***Regional Reward Guidance***, an inference strategy that samples from an optimal distribution with controllable glyph accuracy. Extensive experiments demonstrate that the proposed GlyphPrinter outperforms existing methods in glyph accuracy while maintaining a favorable balance between stylization and precision.