README.md

metadata

title: EDSR Keras
emoji: 🚀
colorFrom: pink
colorTo: yellow
sdk: gradio
sdk_version: 3.1.4b3
app_file: app.py
pinned: false
license: mit

This space is the demo for the EDSR (Enhanced Deep Residual Networks for Single Image Super-Resolution) model. This model surpassed the performace of the current available SOTA models.

Paper Link - https://arxiv.org/pdf/1707.02921

Keras Example link - https://keras.io/examples/vision/edsr/

TODO:

Hack to make this work for any image size. Currently the model takes input of image size 150 x 150. We pad the input image with transparant pixels so that it is a square image, which is a multiple of 150 x 150 Then we chop the image into multiple 150 x 150 sub images Upscale it and stich it together.

The output image might look a bit off, because each sub-image dosent have data about other sub-images. This approach assumes that the subimage has enough data about its surroundings