Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods

• URL: http://arxiv.org/abs/2606.24484v1
• Date: Tue, 23 Jun 2026 12:18:50 GMT
• Title: Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods
• Abstract summary: WordArt (artistic text) features highly customized fonts, textures, and layouts.<n>Existing STR and methods, typically built around regular scene text and fixed-template inputs, struggle to scale to WATER.<n>We construct a 2M synthetic dataset, WATER-S, with the scale improved by hundreds of times compared to existing artistic text data.
• Score: 24.552635491974417
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: WordArt (artistic text) features highly customized fonts, textures, and layouts, making WordArt-oriented scene TExt Recognition (WATER) substantially more challenging than general Scene Text Recognition (STR). Existing STR datasets and methods, typically built around regular scene text and fixed-template inputs, struggle to scale to WATER. Thus, we aim to advance this task from both data and model perspectives. On the data side, we construct a 2M synthetic dataset, WATER-S, with the scale improved by hundreds of times compared to existing artistic text data. WATER-S consists of two complementary subsets. One rendered by an upgraded rendering pipeline (SynthWordArt), which provides highly accurate and controllable synthetic WordArt data. The other is generated by combining Qwen3-VL for prompt mining and Z-Image for image synthesis, which improves the coverage of realistic and diverse data. On the model side, we propose WATERec. It adopts an visual encoder supporting arbitrary-shaped inputs and an autoregressive decoder to model complex layouts, structurally breaking the bottleneck of fixed-template STR on WordArt. Experiments show that this architecture outperforms prior STR methods, achieving state-of-the-art performance on irregular texts such as WordArt. Together with WATER-R, carefully reorganized from existing real STR data, our strong baseline with the new synthetic data and model design reaches 90.40% accuracy on WordArt-Bench, surpassing both general-purpose and OCR-specialized vision-language models by a large margin. Code and data are available at https://github.com/YesianRohn/WATER.

Related papers

• TextSculptor: Training and Benchmarking Scene Text Editing [88.11688559021628]
  We present TextSculptor, a comprehensive framework for data construction and evaluation of scene text editing.<n>TextSculptor improves open-source text editing performance and narrows the gap to proprietary models.
  arXiv  Detail & Related papers  (2026-05-20T12:22:26Z)
• TextGround4M: A Prompt-Aligned Dataset for Layout-Aware Text Rendering [64.22226877213521]
  Despite advances in text-to-image generation, models still struggle to render prompt-specified text with correct spatial layout.<n>We introduce TextGround4M, a dataset of over 4 million prompt-image pairs annotated with span-level text grounded in the prompt and corresponding bounding boxes.<n>We propose a lightweight training strategy for autoregressive T2I models that appends layout-aware span tokens during training, without altering model architecture or inference behavior.
  arXiv  Detail & Related papers  (2026-04-27T13:28:57Z)
• TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering [76.53315206999231]
  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.
  arXiv  Detail & Related papers  (2026-02-24T13:40:23Z)
• UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images [25.895852456869463]
  UTDesign is a unified framework for high-precision stylized text editing and conditional text generation in design images.<n>Our framework supports both English and Chinese scripts.<n>It achieves state-of-the-art performance among open-source methods in terms of stylistic consistency and text accuracy.
  arXiv  Detail & Related papers  (2025-12-23T16:13:55Z)
• Generating Synthetic Invoices via Layout-Preserving Content Replacement [0.0]
  We present a novel pipeline for generating high-fidelity, synthetic invoice documents and their corresponding structured data.<n>Our approach provides a scalable and automated solution to amplify small, private datasets.
  arXiv  Detail & Related papers  (2025-08-04T06:19:34Z)
• WAS: Dataset and Methods for Artistic Text Segmentation [57.61335995536524]
  This paper focuses on the more challenging task of artistic text segmentation and constructs a real artistic text segmentation dataset. We propose a decoder with the layer-wise momentum query to prevent the model from ignoring stroke regions of special shapes. We also propose a skeleton-assisted head to guide the model to focus on the global structure.
  arXiv  Detail & Related papers  (2024-07-31T18:29:36Z)
• TextDiffuser: Diffusion Models as Text Painters [118.30923824681642]
  We introduce TextDiffuser, focusing on generating images with visually appealing text that is coherent with backgrounds. We contribute the first large-scale text images dataset with OCR annotations, MARIO-10M, containing 10 million image-text pairs. We show that TextDiffuser is flexible and controllable to create high-quality text images using text prompts alone or together with text template images, and conduct text inpainting to reconstruct incomplete images with text.
  arXiv  Detail & Related papers  (2023-05-18T10:16:19Z)
• Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation [41.43280922432707]
  We argue for their unification -- we aim for a single model that can compete favourably with two separate state-of-the-art STR and HTR models. We first show that cross-utilisation of STR and HTR models trigger significant performance drops due to differences in their inherent challenges. We then tackle their union by introducing a knowledge distillation (KD) based framework.
  arXiv  Detail & Related papers  (2021-07-26T10:10:34Z)
• SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models [9.934446907923725]
  We introduce a new synthetic text image generator, SynthTIGER, by analyzing techniques used for text image synthesis and integrating effective ones under a single algorithm. In our experiments, SynthTIGER achieves better STR performance than the combination of synthetic datasets.
  arXiv  Detail & Related papers  (2021-07-20T08:03:45Z)
• What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels [53.51264148594141]
  Scene text recognition (STR) task has a common practice: All state-of-the-art STR models are trained on large synthetic data. Training STR models on real data is nearly impossible because real data is insufficient. We show that we can train STR models satisfactorily only with real labeled data.
  arXiv  Detail & Related papers  (2021-03-07T17:05:54Z)

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.