Explorable Super Resolution

Official PyTorch implementation of the paper "Explorable Super Resolution" by Yuval Bahat and Tomer Michaeli (CVPR 2020).

Repository includes:

1. Code for a Graphical User Interface (GUI) allwoing a user to perform explorable super resoution and edit a low-resoultion image in real time. Pre-trained backend models are available for download.
2. Code for training an explorable super resolution model yourself. This model can then be used to replace the available pre-trained models as the GUI backend.
3. Implementation of the Consistency Enforcing Module (CEM) that can wrap any existing (and even pre-trained) super resolution network, modifying its high-resolution outputs to be consistent with the low-resolution input.

BibTex

@article{bahat2019explorable, title={Explorable Super Resolution},
  author={Bahat, Yuval and Michaeli, Tomer},
  journal={arXiv preprint arXiv:1912.01839}, year={2019}
}

Table of Contents

1. Dependencies
2. Codes

Dependencies

• Python 3 (Recommend to use Anaconda)
• PyTorch >= 1.1.0
• NVIDIA GPU + CUDA
• Python packages: pip install numpy opencv-python lmdb

Codes

We provide a detailed explaination of the code framework in ./codes.

Acknowledgement

• Code architecture is based on an older version of BasicSR.