Participants were tasked with developing a machine learning model for generating materials based on given textures, with the total volume of completed tasks exceeding 100 GB. Together, the competing teams spent over 1,600 working hours on development on virtual machines provided by the organisers. The Neurathon was supported by nine mentors and was organised in collaboration with the Faculty of Mathematics and Physics of the UK, the Faculty of Information Technology of the CTU and the Faculty of Electrical Engineering of the CTU. In the competition, the team assembled by Professor Daniel Sýkora from the Department of Computer Graphics and Interaction at the CTU Faculty of Science met competition from students of art, computer science and mathematics. The evaluation system published only automatic results, and the winner was decided by a six-member expert jury. Thus, tension prevailed until the last moment when the first places were announced. "When they announced the second place, we knew that we either had everything - or nothing," said Radim Špetlík on behalf of the whole team.
About Chaos
Chaos is one of the world's largest 3D visualisation companies and has been working with architects, artists and designers for over 20 years. "I am very pleased that the event attracted attendees with diverse backgrounds - students, researchers and professionals from the fields of computer vision, rendering, 3D visualization, data science and machine learning. I was very impressed by their determination to develop a solution to a complex problem in a limited timeframe. The best part of Neurathon was that we had the opportunity to meet other people interested in the combination of computer graphics and artificial intelligence," says Vladimir Koylazov, co-founder of Chaos and Head of Innovation.
