The challenge datasets are hosted on Zenodo

The challenge is hosted on Codalab

Welcome to The Exoplanet Imaging Data Challenge, a community-wide effort to compare algorithms for detecting exoplanets with ground-based high-contrast imaging. The challenge is organized in collaboration with several members of the high-contrast imaging community and had direct support from the Grenoble Alpes Data Institute (Université Grenoble Alpes, France).

In the spirit of openness, we exclusively rely on open source tools for conducting this competition: this website is hosted on GitHub, the implementations of the metrics and backend algorithms (Python code) are stored in the exoimaging extras repository, and Codalab, a framework for accelerating reproducible computational research, was selected to host the competition. Moreover, our plan is to release all the contributed datasets (nineteen in total from 5 different instruments) at the end of the competition as well as the results of the challenge. Finally, this challenge is open to anyone who is interested in participating!

For information about the data challenge explore the "description" pull-down menu on the top of the page: objectives section motivates the realization of this challenge, sub-challenges presents two separate challenges that will be running in parallel, datasets section describes the data formats for each sub-challenge, submissions details the formats and contents of each participants' submission, and finally in the metrics section describes the metrics used in this competition and the service/framework used to host the scoreboards.

What's new:

Data is ready!
During the past few months, we have reached out to several instrument scientists requesting datasets that could be used in... [Read More]