This repo contains implementations of papers related to Image Segmentation and Super Resolution. Many more papers to come.
- Perceptual Losses for Real-Time Style Transfer and Super Resolution
- Checkerboard artifact free sub-pixel convolution
- Enhanced Deep Residual Networks for Single Image Super-Resolution
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
- Pytorch>=0.3
- Fastai
$ python super.py
- ImageNet 10% sample
We're making use of Pixel shuffle
Original image
Output from Model (Using only Perceptual Loss and without icnr initialization
Input image
Output from Model (Using only Perceptual Loss and with icnr initialization