GDC + VRDC 2019 Session Scheduler

View, browse and sort the ever-growing list of sessions by pass type, track, and format. With this Session Scheduler, you can build your schedule in advance and access it during the show via export or with the GDC Mobile App, once live. Sessions do fill up so please arrive early to sessions that you would like to attend. Adding a session to your schedule does not guarantee you a seat.

Assisted Artistry: Applying Deep Learning to Games Content Creation

Natasha Tatarchuk (Graphics Director, Unity Technologies)

Pass Type: All Access, GDC Conference + Summits, GDC Conference - Get your pass now!

Topic: Programming

Format: Session

Vault Recording: Video

Player expectations and ever-increasing hardware capabilities continuously raise the bar for content fidelity in games. This is further fueled by the latest generations of consumer consoles which support 4K resolution rendering and even 8K textures, all while trying to satisfy games’ desires for hours of unique content. It's not just the expectations of increased quality, but expectations of increased scope of content that has game industry struggling to keep up, punctuated by huge rises in production costs over the last decade. This presentation seeks to explore the opportunities to apply deep learning to the problems of game content creation with a focus on pragmatic integration into game tool pipelines and runtime.

Takeaway

In this session, the attendees will learn the practical approaches for applying deep learning techniques to the content creation workflows for games resources, learn about how to tackle constraints, important for efficient content generation in practical game pipelines.

Intended Audience

This presentation is targeted for anyone curious about how to improve the iteration loop for content creation: developers of artist tools pipelines for games production or any real-time content. While the presentation will be technical, it will assume no prior knowledge of deep learning, convolutional neural networks or inference. Familiarity with game content creation pipelines is a major plus, as well as deep interest in improving lives of world-building artists and designers.