thangvubk / PESR

Official code (Pytorch) for paper Perception-Enhanced Single Image Super-Resolution via Relativistic Generative Networks

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

PESR

Official implementation for Perception-Enhanced Single Image Super-Resolution via Relativistic Generative Networks ECCV Workshop 2018

Citation

Please our project if it is helpful for your research

@InProceedings{Vu_2018_ECCV_Workshops},
author = {Vu, Thang and Luu, Tung M. and Yoo, Chang D.},
title = {Perception-Enhanced Image Super-Resolution via Relativistic Generative Adversarial Networks},
booktitle = {The European Conference on Computer Vision (ECCV) Workshops},
month = {September},
year = {2018}
}

PSNR vs PESR

Dependencies

  • Nvidia GPUs (training takes 1 day on 4 Titan Xp GPUs)
  • At least 16G RAM
  • Python3
  • Pytorch 0.4
  • tensorboardX
  • tqdm
  • imageio

Datasets, models, and results

Dataset

  • Train: DIV2K (800 2K-resolution images)
  • Valid (for visualization): DIV2K (100 val images), PIRM (100 self-val images)
  • Test: Set5, Set14, B100, Urban100, PIRM (100 self-val images), DIV2K (100 val images)
  • Download train+val+test datasets
  • Download test only dataset

Pretrained models

  • Download pretrained models including 1 PSNR-optimized model and 1 perception-optimized model

Paper results

Quick start

  • Download test dataset and put into data/origin/ directory
  • Download pretrained model and put into check_point directory
  • Run python test.py --dataset <DATASET_NAME>
  • Results will be saved into results/ directory

Training

  • Download train+val+test dataset and put into data/origin directory
  • Pretrain with L1 loss: python train.py --phase pretrain --learning_rate 1e-4
  • Finetune on pretrained model with GAN: python train.py
  • Models with be saved into check_point/ direcory

Visualization

  • Start tensorboard: tensorboard --logdir check_point
  • Enter: YOUR_IP:6006 to your web browser.
  • Tensorboard when finetuning on pretrained model should be similar to:

Tensorboard

Tensorboard_imgs

Comprehensive testing

  • Test perceptual model: follow Quick start
  • Interpolate between perceptual model and PSNR model: python test.py --dataset <DATASET> --alpha <ALPHA> (with alpha being perceptual weight)
  • Test perceptual quality: refer to PIRM validation code

Quantitative and Qualitative results

RED and BLUE indicate best and second best respectively.

References

About

Official code (Pytorch) for paper Perception-Enhanced Single Image Super-Resolution via Relativistic Generative Networks


Languages

Language:Python 100.0%