StyleText: A Large-Scale Dataset and Benchmark for Stylized Scene Text Inpainting
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909052304359424 |
|---|---|
| author | Simonyan, Aleksandr Jindal, Nipun |
| author_facet | Simonyan, Aleksandr Jindal, Nipun |
| contents | We present StyleText, a large-scale dataset and benchmark for localized scene-text inpainting with style preservation. StyleText contains 28,518 image-mask-prompt triplets grouped into 9,932 scene families, enabling controlled evaluation of text legibility and visual consistency under shared scene context. We construct the dataset with an automated pipeline that combines LLM prompt templating, Flux-based source generation with key-value (KV) cache injection, OCR-based semantic filtering, polygon mask extraction, and mask-conditioned FluxFill augmentation. We define a reproducible evaluation protocol using normalized OCR metrics (word accuracy and character error rate) and CLIP image-image similarity with explicit preprocessing. A FluxFill+LoRA baseline trained on StyleText improves OCR accuracy substantially over initialization while maintaining scene style consistency, establishing a strong reference point for future comparisons. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17309 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | StyleText: A Large-Scale Dataset and Benchmark for Stylized Scene Text Inpainting Simonyan, Aleksandr Jindal, Nipun Computer Vision and Pattern Recognition Artificial Intelligence We present StyleText, a large-scale dataset and benchmark for localized scene-text inpainting with style preservation. StyleText contains 28,518 image-mask-prompt triplets grouped into 9,932 scene families, enabling controlled evaluation of text legibility and visual consistency under shared scene context. We construct the dataset with an automated pipeline that combines LLM prompt templating, Flux-based source generation with key-value (KV) cache injection, OCR-based semantic filtering, polygon mask extraction, and mask-conditioned FluxFill augmentation. We define a reproducible evaluation protocol using normalized OCR metrics (word accuracy and character error rate) and CLIP image-image similarity with explicit preprocessing. A FluxFill+LoRA baseline trained on StyleText improves OCR accuracy substantially over initialization while maintaining scene style consistency, establishing a strong reference point for future comparisons. |
| title | StyleText: A Large-Scale Dataset and Benchmark for Stylized Scene Text Inpainting |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.17309 |