Codes and models for the SIGGRAPH Asia 2018 paper "Image Super-Resolution via Deterministic-Stochastic Synthesis and Local Statistical Rectification".

By Weifeng Ge, Yizhou Yu

Department of Computer Science, The University of Hong Kong

0. Introduction
1. Citation
2. Pipeline
3. Codes and Installation
4. Models
5. Results

This repository contains the codes and models described in the paper "Image Super-Resolution via Deterministic-Stochastic Synthesis and Local Statistical Rectification"(https://arxiv.org/pdf/1809.06557.pdf). These models are trained and tested on the dataset of NTIRE 2017 DIV2K super resolution track.

Note

0. All algorithms are implemented based on the deep learning framework Caffe.
1. Please add the additional layers used into your own Caffe to run the training codes.

If you use these codes and models in your research, please cite:

   @inproceedings{ge2018image,
           title={Image super-resolution via deterministic-stochastic synthesis and local statistical rectification},
           author={Ge, Weifeng and Gong, Bingchen and Yu, Yizhou},
           booktitle={SIGGRAPH Asia 2018 Technical Papers},
           pages={260},
           year={2018},
           organization={ACM}
   }