What is it about?
We perform fast single image super-resolution with flexible magnification for natural images. A novel coarse-to-fine super-resolution framework is developed for the magnification that is factorized into a maximum integer component and the quotient. Specifically, our framework is embedded with a light-weight upscale network for super-resolution with the integer scale factor, followed by the fine-grained network to guide interpolation on feature maps as well as to generate the super-resolved image.
Featured Image
Photo by Markus Spiske on Unsplash
Why is it important?
Our method can handle arbitrary decimal scale factors for super-resolution rather than single fixed integer scale factors, which makes our design more practical. The proposed network is light-weight and have much less computional burden.
Perspectives
Previous efficient methods are totally focused on building models for fixed integer scale factors. We try to find out a more practical method for natural scenario super-resolution. That means arbitrary scale factors should be supported and super-resolution procedure should be fast and flexible enough.
zhichao fu
Read the Original
This page is a summary of: A Coarse-to-fine Approach for Fast Super-Resolution with Flexible Magnification, December 2021, ACM (Association for Computing Machinery),
DOI: 10.1145/3469877.3490564.
You can read the full text:
Contributors
The following have contributed to this page
