TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912928411680768 |
|---|---|
| author | Zhu, Hanshen Liu, Yuliang Wu, Xuecheng Wang, An-Lan Feng, Hao Yang, Dingkang Feng, Chao Huang, Can Tang, Jingqun Bai, Xiang |
| author_facet | Zhu, Hanshen Liu, Yuliang Wu, Xuecheng Wang, An-Lan Feng, Hao Yang, Dingkang Feng, Chao Huang, Can Tang, Jingqun Bai, Xiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_20903 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering Zhu, Hanshen Liu, Yuliang Wu, Xuecheng Wang, An-Lan Feng, Hao Yang, Dingkang Feng, Chao Huang, Can Tang, Jingqun Bai, Xiang Computer Vision and Pattern Recognition 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. |
| title | TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.20903 |