Search Results for author:
Found 3 papers, 2 papers with code
Learn From Orientation Prior for Radiograph Super-Resolution: Orientation Operator Transformer
Conclusions: In this study, we propose a novel framework called $O^{2}$former for radiological image super-resolution tasks, which improves the reconstruction model's performance by introducing an orientation operator and multi-scale feature fusion strategy.
A Scene-Text Synthesis Engine Achieved Through Learning from Decomposed Real-World Data
Some of these studies have proposed generating scene-text images through learning; however, owing to the absence of a suitable training dataset, unsupervised frameworks have been explored to learn from existing real-world data, which might not yield reliable performance.
Stroke-Based Scene Text Erasing Using Synthetic Data for Training
To compensate for the lack of pairwise real-world data, we made considerable use of synthetic text after additional enhancement and subsequently trained our model only on the dataset generated by the improved synthetic text engine.
