Unwarping Screen Content Images via Structure-texture Enhancement Network and Transformation Self-estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908329405579264 |
|---|---|
| author | Xiao, Zhenzhen Liu, Heng Hu, Bingwen |
| author_facet | Xiao, Zhenzhen Liu, Heng Hu, Bingwen |
| contents | While existing implicit neural network-based image unwarping methods perform well on natural images, they struggle to handle screen content images (SCIs), which often contain large geometric distortions, text, symbols, and sharp edges. To address this, we propose a structure-texture enhancement network (STEN) with transformation self-estimation for SCI warping. STEN integrates a B-spline implicit neural representation module and a transformation error estimation and self-correction algorithm. It comprises two branches: the structure estimation branch (SEB), which enhances local aggregation and global dependency modeling, and the texture estimation branch (TEB), which improves texture detail synthesis using B-spline implicit neural representation. Additionally, the transformation self-estimation module autonomously estimates the transformation error and corrects the coordinate transformation matrix, effectively handling real-world image distortions. Extensive experiments on public SCI datasets demonstrate that our approach significantly outperforms state-of-the-art methods. Comparisons on well-known natural image datasets also show the potential of our approach for natural image distortion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15108 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unwarping Screen Content Images via Structure-texture Enhancement Network and Transformation Self-estimation Xiao, Zhenzhen Liu, Heng Hu, Bingwen Computer Vision and Pattern Recognition While existing implicit neural network-based image unwarping methods perform well on natural images, they struggle to handle screen content images (SCIs), which often contain large geometric distortions, text, symbols, and sharp edges. To address this, we propose a structure-texture enhancement network (STEN) with transformation self-estimation for SCI warping. STEN integrates a B-spline implicit neural representation module and a transformation error estimation and self-correction algorithm. It comprises two branches: the structure estimation branch (SEB), which enhances local aggregation and global dependency modeling, and the texture estimation branch (TEB), which improves texture detail synthesis using B-spline implicit neural representation. Additionally, the transformation self-estimation module autonomously estimates the transformation error and corrects the coordinate transformation matrix, effectively handling real-world image distortions. Extensive experiments on public SCI datasets demonstrate that our approach significantly outperforms state-of-the-art methods. Comparisons on well-known natural image datasets also show the potential of our approach for natural image distortion. |
| title | Unwarping Screen Content Images via Structure-texture Enhancement Network and Transformation Self-estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.15108 |