Skip to content
Projekte

cvlab-yonsei/PISR has 249 GitHub stars and 32 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-19 02:49 UTC. Last push 2020-09-25.

So werden diese Zahlen gemessen

Gemessener Sternzuwachs

in 24h
0
in 7 days
Verlauf wird gesammelt
in 15 days
Verlauf wird gesammelt
in 1 month
Verlauf wird gesammelt

Nettoänderungen in überlappenden Zeiträumen, keine Tagessummen. Fehlende Messwerte bleiben leer. Sterne zeigen Interesse, nicht Qualität.

Über uns

An official implementation of "Learning with Privileged Information for Efficient Image Super-Resolution" (ECCV2020) in PyTorch.

Maschinelles Lernen

README.md

Original

PyTorch implementation of PISR

This is an official implementation of the paper "Learning with Privileged Information for Efficient Image Super-Resolution", accepted to ECCV2020.

This work effectively boosts the performance of FSRCNN by exploiting a distillation framework, treating HR images as privileged information.

For more information, checkout the project site [website] and the paper [PDF].

Overview of our framework

no_image

Getting started

Dependencies

Docker

We provide a Dockerfile to reproduce our work easily.

$ docker build -t pisr:latest . # or docker pull wonkyunglee/pytorch_pisr:latest
$ docker run -it -v <working_dir>:/data -w /data pisr:latest /bin/bash

Datasets

  • For training and validation
    • DIV2K
  • For evaluation
    • Set5
    • Set14
    • B100
    • Urban100

Please download DIV2K dataset from here and other benchmark datasets from here.

After download all datasets, the folder data should be like this:

    data
    ├── benchmark
    │   ├── B100
    │   ├── Set14
    │   ├── Set5
    │   └── Urban100
    │       ├── HR
    │       └── LR_bicubic
    │           ├── X2
    │           ├── X3
    │           └── X4
    │      
    └── DIV2K
        ├── DIV2K_train_HR
        └── DIV2K_train_LR_bicubic
            ├── X2
            ├── X3
            └── X4

Training

First, clone our github repository.

$ git clone https://github.com/yonsei-cvlab/PISR.git

To train our teacher model, run the following script.

$ python step1_train_teacher.py --config configs/fsrcnn/step1.yml

To train our student model, run the following script.

$ python step2_train_student.py --config configs/fsrcnn/step2.yml

Using the pretrained models

  • Download pre-trained weights for teacher model into results/fsrcnn/fsrcnn_teacher/checkpoint/ folder.
    Link: [weights]
  • Download pre-trained weights for student model into results/fsrcnn/fsrcnn_student/checkpoint/ folder.
    Link: [weights]

Evaluation

To evaluate our student model, run following script. Benchmark datasets can be choosed by editing the config file configs/fsrcnn/base.ram.yml.

$ python evaluate.py --config configs/fsrcnn/step2.yml

Citation

@inproceedings{lee2020pisr,
    author={Lee, Wonkyung and Lee, Junghyup and Kim, Dohyung and Ham, Bumsub},
    title={Learning with Privileged Information for Efficient Image Super-Resolution},
    booktitle={Proceedings of European Conference on Computer Vision},
    year={2020},
}

Credit

Some parts of this code (e.g., data_loader) are based on EDSR-PyTorch repository.