GDC is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

GDC + VRDC 2019 Session Scheduler

View, browse and sort the ever-growing list of GDC sessions by pass type, track, format, and more! With Session Scheduler, create an account to build your own GDC schedule and access it anywhere, including on the GDC app, once live.

If you've registered for GDC, you can use the same login credentials. Adding a session to your schedule does not guarantee you a seat. Sessions do fill up, so please arrive early to sessions that you would like to attend.

Super Powering Technical Artists Using Deep Learning

Cesar Romero (Principal Machine Learning Engineer, Unity Technologies)

Location: Room 2001, West Hall

Date: Thursday, March 21

Time: 3:00pm - 3:30pm

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

Topic: Visual Arts

Format: Session

Vault Recording: Video

Audience Level: All

Many people know that machine learning can be used to classify text or images, recommend products, understand your voice or translate documents. Fewer know that it can also be used to generate high-quality content. In this talk, the speaker explains generative models and shows why they've become popular in the last 4 years. The speaker will present multiple demos and applications of how these models can give superpowers to technical artists to assist them in creating delightful experiences, generating variations of textures, enabling super-resolution, transferring style across objects, powering procedural level creation, and sketching or even reproducing a scene starting from just a photograph!


From this session, artists and developers learn how machine learning can apply to the process of world-building to solve time-consuming tasks normally handled manually by a team of artists. The audience learns how machine learning can save development and artistic time, enabling greater focus on creative pursuits rather than the tedium of repetitive tasks.

Intended Audience

The target audience is primarily technical artists, but also game developers interested or involved in world building. There is no strong technical knowledge required to understand the demos, just an appreciation for the visual content in games and the process of creating delightful game worlds.