Leveraging text semantics for enhanced scene text image super-resolution
In recent years, due to the development of neural networks, super-resolution technology has made unprecedented progress. However, most existing super-resolution methods treat scene text images as normal images, ignoring the text information within them. This paper proposes to incorporate categorical...
Saved in:
| Main Authors: | Li Chen, Jinsong Wu, Yicheng Liu |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2025-06-01
|
| Series: | Intelligent and Converged Networks |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.23919/ICN.2025.0009 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Single-Character-Based Embedding Feature Aggregation Using Cross-Attention for Scene Text Super-Resolution
by: Meng Wang, et al.
Published: (2025-04-01) -
Better Skeleton Better Readability: Scene Text Image Super-Resolution via Skeleton-Aware Diffusion Model
by: Shrey Singh, et al.
Published: (2024-01-01) -
Cascaded Dual-Inpainting Network for Scene Text
by: Chunmei Liu
Published: (2025-07-01) -
Text Font Correction and Alignment Method for Scene Text Recognition
by: Liuxu Ding, et al.
Published: (2024-12-01) -
Turkish scene text recognition: Introducing extensive real and synthetic datasets and a novel recognition model
by: Serdar Yıldız
Published: (2024-12-01)