TextSculptor: Training and Benchmarking Scene Text Editing
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914583102357504 |
|---|---|
| author | Lin, Yiheng Jiao, Siyu Lan, Xiaohan Zhou, Wei She, Qi Yu, Fei Chen, Heyun Wang, Zhengwei Chen, Jinghuan Li, Moran Yu, Yingchen Feng, Zijian Zhao, Yao Wei, Yunchao Zhong, Yujie |
| author_facet | Lin, Yiheng Jiao, Siyu Lan, Xiaohan Zhou, Wei She, Qi Yu, Fei Chen, Heyun Wang, Zhengwei Chen, Jinghuan Li, Moran Yu, Yingchen Feng, Zijian Zhao, Yao Wei, Yunchao Zhong, Yujie |
| contents | Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have substantially improved prompt-driven image editing. However, scene text editing remains challenging, as it requires models to precisely modify textual content while preserving visual realism and non-target regions. Current open-source models still lag behind proprietary systems, largely due to the scarcity of high-quality training data and the lack of standardized benchmarks tailored to text editing. To address these challenges, we present TextSculptor, a comprehensive framework for data construction and evaluation of scene text editing. We first develop an automated data construction pipeline that combines text-aware image synthesis with programmatic text rendering and compositing. Based on this pipeline, we build TextSculpt-Data, a large-scale dataset containing 3.2M training samples, including 1.2M OCR-verified text-to-image samples and 2M paired text editing samples with naturally aligned source-target images and strong background consistency. We further introduce TextSculpt-Bench, a benchmark covering four fundamental text editing tasks: text addition, text replacement, text removal, and hybrid editing. To support reliable evaluation, we design a tailored protocol that measures text accuracy, visual quality, and background preservation through OCR-based text alignment, multimodal judgment, and background-region similarity. Extensive experiments show that TextSculptor improves open-source text editing performance and narrows the gap to proprietary models. The data and benchmark are available at https://github.com/linyiheng123/TextSculptor. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_21090 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TextSculptor: Training and Benchmarking Scene Text Editing Lin, Yiheng Jiao, Siyu Lan, Xiaohan Zhou, Wei She, Qi Yu, Fei Chen, Heyun Wang, Zhengwei Chen, Jinghuan Li, Moran Yu, Yingchen Feng, Zijian Zhao, Yao Wei, Yunchao Zhong, Yujie Computer Vision and Pattern Recognition Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have substantially improved prompt-driven image editing. However, scene text editing remains challenging, as it requires models to precisely modify textual content while preserving visual realism and non-target regions. Current open-source models still lag behind proprietary systems, largely due to the scarcity of high-quality training data and the lack of standardized benchmarks tailored to text editing. To address these challenges, we present TextSculptor, a comprehensive framework for data construction and evaluation of scene text editing. We first develop an automated data construction pipeline that combines text-aware image synthesis with programmatic text rendering and compositing. Based on this pipeline, we build TextSculpt-Data, a large-scale dataset containing 3.2M training samples, including 1.2M OCR-verified text-to-image samples and 2M paired text editing samples with naturally aligned source-target images and strong background consistency. We further introduce TextSculpt-Bench, a benchmark covering four fundamental text editing tasks: text addition, text replacement, text removal, and hybrid editing. To support reliable evaluation, we design a tailored protocol that measures text accuracy, visual quality, and background preservation through OCR-based text alignment, multimodal judgment, and background-region similarity. Extensive experiments show that TextSculptor improves open-source text editing performance and narrows the gap to proprietary models. The data and benchmark are available at https://github.com/linyiheng123/TextSculptor. |
| title | TextSculptor: Training and Benchmarking Scene Text Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.21090 |