TBStar-Edit: From Image Editing Pattern Shifting to Consistency Enhancement
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914094901100544 |
|---|---|
| author | Fang, Hao Zhan, Zechao Feng, Weixin Huang, Ziwei Li, Xubin Ge, Tiezheng |
| author_facet | Fang, Hao Zhan, Zechao Feng, Weixin Huang, Ziwei Li, Xubin Ge, Tiezheng |
| contents | Recent advances in image generation and editing technologies have enabled state-of-the-art models to achieve impressive results in general domains. However, when applied to e-commerce scenarios, these general models often encounter consistency limitations. To address this challenge, we introduce TBStar-Edit, an new image editing model tailored for the e-commerce domain. Through rigorous data engineering, model architecture design and training strategy, TBStar-Edit achieves precise and high-fidelity image editing while maintaining the integrity of product appearance and layout. Specifically, for data engineering, we establish a comprehensive data construction pipeline, encompassing data collection, construction, filtering, and augmentation, to acquire high-quality, instruction-following, and strongly consistent editing data to support model training. For model architecture design, we design a hierarchical model framework consisting of a base model, pattern shifting modules, and consistency enhancement modules. For model training, we adopt a two-stage training strategy to enhance the consistency preservation: first stage for editing pattern shifting, and second stage for consistency enhancement. Each stage involves training different modules with separate datasets. Finally, we conduct extensive evaluations of TBStar-Edit on a self-proposed e-commerce benchmark, and the results demonstrate that TBStar-Edit outperforms existing general-domain editing models in both objective metrics (VIE Score) and subjective user preference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04483 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TBStar-Edit: From Image Editing Pattern Shifting to Consistency Enhancement Fang, Hao Zhan, Zechao Feng, Weixin Huang, Ziwei Li, Xubin Ge, Tiezheng Computer Vision and Pattern Recognition Recent advances in image generation and editing technologies have enabled state-of-the-art models to achieve impressive results in general domains. However, when applied to e-commerce scenarios, these general models often encounter consistency limitations. To address this challenge, we introduce TBStar-Edit, an new image editing model tailored for the e-commerce domain. Through rigorous data engineering, model architecture design and training strategy, TBStar-Edit achieves precise and high-fidelity image editing while maintaining the integrity of product appearance and layout. Specifically, for data engineering, we establish a comprehensive data construction pipeline, encompassing data collection, construction, filtering, and augmentation, to acquire high-quality, instruction-following, and strongly consistent editing data to support model training. For model architecture design, we design a hierarchical model framework consisting of a base model, pattern shifting modules, and consistency enhancement modules. For model training, we adopt a two-stage training strategy to enhance the consistency preservation: first stage for editing pattern shifting, and second stage for consistency enhancement. Each stage involves training different modules with separate datasets. Finally, we conduct extensive evaluations of TBStar-Edit on a self-proposed e-commerce benchmark, and the results demonstrate that TBStar-Edit outperforms existing general-domain editing models in both objective metrics (VIE Score) and subjective user preference. |
| title | TBStar-Edit: From Image Editing Pattern Shifting to Consistency Enhancement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.04483 |