• About
  • Competitions
  • PROBA-V Super Resolution
  • Register
  • Sign In
    Forgot password?
    GitHub
    By logging in with Github you accept our Privacy Policy
PROBA-V Super Resolution
  • Home
  • Problem
  • Rules
  • Data
  • Submission Rules
  • Scoring
  • Kelvins Day
  • Post Mortem
  • Post Mortem Leaderboard
  • Leaderboard
  • Results
  • Discussion
  • Resources
Timeline

Nov. 1, 2018, 5 a.m. UTC

June 1, 2019, 6 a.m. UTC

The competition is over.

Submission Rules

How to make a submission

The format of submission is a single .zip-file that should include 290 super-resolution images, one for each data member in the test-set.

Each submitted image must be in .png-format, saved in 16bit grayscale in a 384x384 pixel shape. The file should be named "imgsetxxxx.png" where xxxx corresponds to the id of the test-set (case sensitive).

Validation in detail

The validation step performs the following checks in that order:

  • size of file is less than 100MB
  • file needs to have the extension ".zip"
  • file needs to be a valid zip-file (no corrupt header, no other compression format allowed)
  • none of the 290 images are missing
  • there are no additional files in the zip except the 290 images
  • the images in the zip are named from "imgset1160.png" to "imgset1449.png"
  • every image is 16bit grayscale png
  • every image has a resolution of 384x384 pixels

If one of the checks fails, you will be notified with a corresponding error message. If your submission is valid, it will be evaluated and be shown on the public leader-board as soon as its score) has been computed (might take a minute).

Example submission

You can download the following python script which will generate an example submission for you.

  • generate_sample_submission.py

To run the script you need

  • Python 3
  • Numpy
  • scikit-image

Assuming that all data is available at a local folder data, run the script with:

python generate_sample_submission.py data submission

If everything works out, it will create a folder submission, containing some images and a .zip-file which you can use to test the system.

The algorithm in this script takes all low resolution images that have the maximum amount of clear pixels, computes a bicubic upscaling by a factor of 3 and averages their pixel intensities. The Scoring of these images (in terms of their \(cPSNR\)) constitutes our baseline of value 1 for ranking submissions. Thus, in order to improve upon bicubic upscaling, a submission needs to receive a score lower than 1.

Created by the Advanced Concepts Team, Copyright © European Space Agency 2021