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., Seedream4.0, 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.
@article{arxiv.2602.20903,
title = {TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering},
author = {Hanshen Zhu and Yuliang Liu and Xuecheng Wu and An-Lan Wang and Hao Feng and Dingkang Yang and Chao Feng and Can Huang and Jingqun Tang and Xiang Bai},
journal= {arXiv preprint arXiv:2602.20903},
year = {2026}
}
Comments
Accepted by CVPR 2026; Code: https://github.com/CIawevy/TextPecker