Search Results for author:
Found 4 papers, 2 papers with code
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.
Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networks
To address both of the drawbacks, our method adopts two-stage training and network interpolation.
Automatic Generation of Typographic Font from a Small Font Subset
The proposed method uses strokes from given samples for font generation.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
