Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network implemented in Keras
-
Updated
Apr 19, 2019 - Python
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network implemented in Keras
This repository features an image sharpening pipeline using Knowledge Distillation. A high-capacity Restormer acts as the teacher model, while a lightweight Mini-UNet is trained as the student to mimic its performance.
Implementation and training of SRResNet and SRGAN models from scratch using PyTorch for image super-resolution.
Add a description, image, and links to the vgg-loss topic page so that developers can more easily learn about it.
To associate your repository with the vgg-loss topic, visit your repo's landing page and select "manage topics."