TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering

• URL: http://arxiv.org/abs/2602.20903v3
• Date: Thu, 26 Feb 2026 14:04:48 GMT
• Title: TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering
• Authors: Hanshen Zhu, Yuliang Liu, Xuecheng Wu, An-Lan Wang, Hao Feng, Dingkang Yang, Chao Feng, Can Huang, Jingqun Tang, Xiang Bai,
• Abstract summary: TextPecker is a plug-and-play structural anomaly perceptive RL strategy.<n>It mitigates noisy reward signals and works with any textto-image generators.<n>It significantly yields average gains of 4% in structural fidelity and 8.7% in semantic alignment for Chinese text rendering.
• Score: 76.53315206999231
• License: http://creativecommons.org/licenses/by/4.0/
• 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., 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.

Related papers

• TextBoost: Boosting Scene Text Fidelity in Ultra-low Bitrate Image Compression [11.661973720343546]
  Region-of-interest bit allocation can prioritize text but degrades global fidelity, leading to a trade-off between local accuracy and overall image quality.<n>We incorporate auxiliary textual information extracted by OCR and transmitted with negligible overhead, enabling the decoder to leverage this semantic guidance.<n>Tests 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)
  arXiv  Detail & Related papers  (2026-03-04T14:35:10Z)
• Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization [50.13408999553116]
  We propose RL-Text2Vis, the first reinforcement learning framework for Text2Vis generation.<n>Our method uses a novel multi-objective reward that jointly optimize textual accuracy, code validity, and visualization quality.<n>Our results establish GRPO as an effective strategy for structured, multimodal reasoning in visualization generation.
  arXiv  Detail & Related papers  (2026-01-08T04:29:07Z)
• Interleaving Reasoning for Better Text-to-Image Generation [83.69082794730664]
  We introduce Interleaving Reasoning Generation (IRG), a framework that alternates between text-based thinking and image synthesis.<n>To train IRG effectively, we propose Interleaving Reasoning Generation Learning (IRGL), which targets two sub-goals.<n>Experiments show SoTA performance, yielding absolute gains of 5-10 points on GenEval, WISE, TIIF, GenAI-Bench, and OneIG-EN.
  arXiv  Detail & Related papers  (2025-09-08T17:56:23Z)
• Qwen-Image Technical Report [86.46471547116158]
  We present Qwen-Image, an image generation foundation model that achieves significant advances in complex text rendering and precise image editing.<n>We design a comprehensive data pipeline that includes large-scale data collection, filtering, annotation, synthesis, and balancing.<n>Qwen-Image performs exceptionally well in alphabetic languages such as English, and also achieves remarkable progress on more challenging logographic languages like Chinese.
  arXiv  Detail & Related papers  (2025-08-04T11:49:20Z)
• Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoders [14.655107789528673]
  We introduce a novel diffusion-based SR framework, namely TADiSR, which integrates text-aware attention and joint segmentation decoders.<n>We propose a complete pipeline for synthesizing high-quality images with fine-grained full-image text masks.<n>Our approach substantially enhances text legibility in super-resolved images, achieving state-of-the-art performance across multiple evaluation metrics.
  arXiv  Detail & Related papers  (2025-06-05T05:23:10Z)
• Robustness in Both Domains: CLIP Needs a Robust Text Encoder [55.348860778166426]
  LEAF is an efficient adversarial finetuning method for the text domain, with the ability to scale to large CLIP models.<n>Our models significantly improve the zero-shot adversarial accuracy in the text domain, while maintaining the vision performance provided by robust image encoders.<n>We show that robust text encoders facilitate better reconstruction of input text from its embedding via direct optimization.
  arXiv  Detail & Related papers  (2025-06-03T19:57:09Z)
• GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing [23.64662356622401]
  We present GlyphMastero, a specialized glyph encoder designed to guide the latent diffusion model for generating texts with stroke-level precision.<n>Our method achieves an 18.02% improvement in sentence accuracy over the state-of-the-art scene text editing baseline.
  arXiv  Detail & Related papers  (2025-05-08T03:11:58Z)
• ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Models [52.23899502520261]
  We introduce a novel framework named, ARTIST, which incorporates a dedicated textual diffusion model to focus on the learning of text structures specifically.<n>We finetune a visual diffusion model, enabling it to assimilate textual structure information from the pretrained textual model.<n>This disentangled architecture design and training strategy significantly enhance the text rendering ability of the diffusion models for text-rich image generation.
  arXiv  Detail & Related papers  (2024-06-17T19:31:24Z)
• TextCraftor: Your Text Encoder Can be Image Quality Controller [65.27457900325462]
  Diffusion-based text-to-image generative models, e.g., Stable Diffusion, have revolutionized the field of content generation. We propose a proposed fine-tuning approach, TextCraftor, to enhance the performance of text-to-image diffusion models.
  arXiv  Detail & Related papers  (2024-03-27T19:52:55Z)
• Spectral Normalization and Dual Contrastive Regularization for Image-to-Image Translation [9.029227024451506]
  We propose a new unpaired I2I translation framework based on dual contrastive regularization and spectral normalization. We conduct comprehensive experiments to evaluate the effectiveness of SN-DCR, and the results prove that our method achieves SOTA in multiple tasks.
  arXiv  Detail & Related papers  (2023-04-22T05:22:24Z)
• A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution [13.934846626570286]
  Scene text image super-resolution aims to increase the resolution and readability of the text in low-resolution images. It remains difficult to reconstruct high-resolution images for spatially deformed texts, especially rotated and curve-shaped ones. We propose a CNN based Text ATTention network (TATT) to address this problem.
  arXiv  Detail & Related papers  (2022-03-17T15:28:29Z)
• DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis [80.54273334640285]
  We propose a novel one-stage text-to-image backbone that directly synthesizes high-resolution images without entanglements between different generators. We also propose a novel Target-Aware Discriminator composed of Matching-Aware Gradient Penalty and One-Way Output. Compared with current state-of-the-art methods, our proposed DF-GAN is simpler but more efficient to synthesize realistic and text-matching images.
  arXiv  Detail & Related papers  (2020-08-13T12:51:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.