Image upscaling


Marie-Hélène Burle

Super-resolution—the process of (re)creating high resolution images from low resolution ones—is an old field, but deep neural networks have seen a sudden surge of new and very impressive methods over the past 10 years, from SRCCN to SRGAN to Transformers.

In this webinar, I will give a quick overview of these methods and show how the latest state-of-the-art model—SwinIR—performs on a few test images. We will use PyTorch as our framework.

Slides (Click and wait: this reveal.js presentation is heavy and takes some time to load.)