DAER logo animation

AI in Production

Artificial Intelligence (AI) is a buzzword that has become hard to ignore lately. Despite much attention to the subject at conferences and in the media, it can remain vague what the realistic possibilities are today. In recent years, we have had AI breakthroughs in the field of self-driving cars, voice technology and playing various games. However, a clear picture of how this game, VFX and animation can improve production pipelines is still lacking.

" TETRA, short for TEchnology TRAnsfer, is a practice-oriented research program aimed at projects with a high economic and social value. The aim is to transfer new technologies and knowledge to the professional field."

Game testing, creating animations, or designing realistic conversations are just a few examples in which AI can and will play an important role in the future. DAE-Research started this TETRA project to better map out the possibilities. Together with a guidance group consisting of several Games and VFX companies, we believe that using AI will free up more time for the creative process itself. Collaboration and interaction with the support group ensure that our research is applicable and valuable in the field.The current TETRA is the follow-up to a preparatory year that ended in September 2020. In the preparatory year, various use cases were identified together with the guidance group in which AI will have the most impact.

On January 1, 2021, we started to further develop the use cases and broaden the knowledge and research from the first year. In concrete terms, we offer the companies in the support group the following:

6 validated proof of concepts based on the input received:

  • Basic knowledge about AI & existing tools and methodologies
  • In-depth knowledge of AI applied to games, VFX and animation
  • Test and compare existing AI tools
  • Workshops to train employees
  • Continuous updates on project results and relevant academic papers through website blog posts and meetings
  • Networking

LATEST USE CASES

Overview: Reinforcement learning in games
In this blog post we give a brief introduction to Reinforcement Learning (RL) and look at a number of applications within the gaming world. The goal is to stimulate your ideas, and also to demonstrate that you don’t have to be an AI expert to get started with these technologies. We look forward to questions or ideas arising from this blog post and are happy to take all input into account in preparation for the planned workshops.
(Automatic) Rigging
To date, creating a rig for a model and assigning the correct blending weights has been a manual process. This rig is required to further animate your model, and is therefore a crucial step in the animation pipeline. In this overview we look at whether it is possible to automate this phase, which would be a big step forward in accelerating the animation pipeline.
Overview: Automatic Rotoscoping
Automatic rotoscoping could speed up a very labor-intensive part of a production. It is therefore interesting to look at where people are so far in research into algorithms that can make this happen. In this blog we look at 4 different, recent techniques and programs that strive for (semi-)automatic rotoscoping.

PROJECT BOOK

Please wait while flipbook is loading. For more related info, FAQs and issues please refer to DearFlip WordPress Flipbook Plugin Help documentation.

RELATED EVENTS

AI in Production Closing Event

08/12/2022
The Square, Luipaardstraat 12a, Kortrijk, Belgium
This event is the result of TETRA AI in Production, a 2-year research project focusing on how AI can be used in game, VFX and animation production. Our researchers have closely followed the developments of AI over the past 3 years. We are excited to continue sharing this knowledge with our steering committee and with anyone interested in developments in this area!

CoG 2021

17/08/2021
Online / Copenhagen, Denmark
Games offer a limitless domain for computational creativity, design, technology, education, social sciences, and artificial intelligence. The annual IEEE Conference on Games (CoG) is a unique forum for cutting-edge research related to game technologies and design, covering scientific, technical, social and human aspects of games. CoG was expressly launched to reflect the changing nature of games as technology and media; where concerns merge, overlap, and cross-pollinate. Beginning as an evolution of the Conference on Computational Intelligence and Games (CIG) and later joined by the International Conference on Virtual Worlds and Games for Serious Applications (VS-Games), CoG brings together leading researchers and practitioners from academia and industry, to share recent advances and co-create future directions. This year’s edition of CoG continues forging the path of attracting an evermore competent and diverse audience. Alongside our traditional types of submission (articles for peer review intended to be included in the conference proceedings), we seek proposals for presentations from both academia and industry in the form of abstracts. Furthermore, it is also possible to apply to present work previously published in the IEEE Transactions on Games journal.

AI Summer School 2021

08/07/2021
Online
In 2021, KU Leuven organised the first edition of the Summer School on the Law, Ethics and Policy of Artificial Intelligence (AI). The Summer School aims to provide a comprehensive overview of the various legal, ethical and policy-related issues around AI and algorithm-driven processes more broadly. As these technologies have a growing impact on all domains of our lives, it becomes increasingly important to map, understand and assess the challenges and opportunities they raise. This requires an interdisciplinary approach, which is why we are collaborating across faculties and departments to organise this Summer School. The programme’s goal is to offer participants the latest insights on AI from various perspectives, and in particular the fields of law, ethics and policy.

PROJECT PARTNERS