The GAN Book: Train stable Generative Adversarial Networks using TensorFlow2, Keras and Python.

A Tensorflow2.0 implementation of Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

SRCNN_SRGAN_ESRGAN_ON_BRAIN_MRI

These scripts were written for my final project; if the topic is of interest to you, feel free to contact me.

Re-Implementation of SRGAN with symmetric padding for a better merged final image (Anysized input with 4x upscaled)

Image Enhancer Super resolution website repository. Main website hosted in Render which is using Rest api to get inference from GCP where model is hosted.

In this project, we implement SRGAN. This paper attempts to upscale images up to a factor of 4x without losing the finer textural details. We extended the scope of this idea to videos. We demonstrate that the model generalizes well on out-of-domain inputs through various biased and unbiased inputs.

Image Impainting and superesolution