Abstract
Visual Text Rendering (VTR) remains a critical challenge in text-to-image generation, where even advanced models frequently produce text with structural anomalies such as distortion, blurriness, and misalignment. However, we find that leading MLLMs and specialist OCR models largely fail to perceive these structural anomalies, creating a critical bottleneck for both VTR evaluation and RL-based optimization. As a result, even state-of-the-art generators (e.g., SeedDream4.0, Qwen-Image) still struggle to render structurally faithful text. To address this, we propose TextPecker, a plug-and-play structural anomaly perceptive RL strategy that mitigates noisy reward signals and works with any textto-image generator. To enable this capability, we construct a recognition dataset with character-level structural-anomaly annotations and develop a stroke-editing synthesis engine to expand structural-error coverage. Experiments show that TextPecker consistently improves diverse text-to-image models; even on the well-optimized Qwen-Image, it significantly yields average gains of 4% in structural fidelity and 8.7% in semantic alignment for Chinese text rendering, establishing a new state-of-the-art in high-fidelity VTR. Our work fills a gap in VTR optimization, providing a foundational step towards reliable and structural faithful visual text generation.
Abstract (translated)
视觉文本渲染（VTR）在文字到图像生成领域仍然是一个关键挑战，即使是最先进的模型也经常产生结构异常的文字，如扭曲、模糊和错位。然而，我们发现领先的多模态语言模型（MLLMs）和专业的OCR模型在识别这些结构异常方面表现不佳，这为VTR评估和基于强化学习的优化造成了重大瓶颈。因此，即使是最先进的生成器（例如SeedDream4.0 和 Qwen-Image），依然难以准确渲染出具有结构一致性的文字。 为了应对这一挑战，我们提出了TextPecker——一种即插即用的感知结构异常的强化学习策略，它可以减少噪声奖励信号，并与任何文本到图像生成模型兼容。为了实现这一点，我们构建了一个包含字符级别结构异常注释的数据集，并开发了一种笔画编辑合成引擎以扩展错误覆盖范围。 实验表明，TextPecker可以持续改进各种不同的文字到图像的模型；即使在已经高度优化的Qwen-Image上，它依然能够显著提升平均4%的文字结构保真度和8.7%的语义对齐度（针对中文文本渲染），确立了高保真VTR的新标杆。我们的工作填补了VTR优化中的空白，并为可靠且具有结构性一致性的视觉文字生成奠定了基础步骤。
URL
https://arxiv.org/abs/2602.20903
