Overview of deep learning methods for super-resolution and test of the latest SwinIR Transformer model
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 SRCNN 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.
Speaker: Marie-Helene Burle