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.

View, browse and sort the ever-growing list of GDC sessions by time, pass type, topic, and format. With GDC 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.

If you've registered for GDC, you can use the same login credentials for your Session Scheduler account. 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.

Technical Artist Summit: Deep Inks: Using Machine Learning to Ink Textures for 'Borderlands 3'

Ryan Smith (Lead Technical Artist, Gearbox Software)

Location: Room 210, South Hall

Date: Tuesday, March 17

Time: 3:50pm - 4:20pm

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

Topic: Visual Arts

Format: Session

Vault Recording: TBD

Audience Level: All

Learn how machine learning was used to automate the incredibly tedious process of adding hand-drawn inks to the textures of Borderlands 3. After an overview of the Borderlands 3 art style, you'll learn why automating the inking pipeline is the holy grail for Gearbox's art department. Gain insights into the steps taken to achieve this goal, including but not limited to selecting the right network architecture, choosing the training curriculum that gives the model the best chance of success, training the model, and wrapping the resulting model into an artist-friendly GUI. This session is aimed primarily at artists and technical artists in hopes that they understand and gain insights into how they can add machine learning to their toolbox.


Attendees will leave with an understanding of how machine learning was used in the Borderlands 3 art production pipeline. The session will also demystify the process of researching and developing their own machine learning projects to apply to their own art pipelines.

Intended Audience

This talk is intended for artists and technical artists above junior level. Knowledge of machine learning is not required, but it may help to review conditional adversarial networks before the session.