You've been logged out of GDC Vault since the maximum users allowed for this account has been reached. To access Members Only content on GDC Vault, please log out of GDC Vault from the computer which last accessed this account.

Click here to find out about GDC Vault Membership options for more users.


Session Name:

Machine Learning Summit: Emotional Neural Style Transfer: Expressing Character AI Emotion through Paintings


Recently machine learning has been applied mostly for asset creations. We take a new step on applying machine learning in game AI to transform the way a character AI expresses its emotion, which generally has been limited to facial expression, body gesture, and vocal intonation. In particular, we adopted neural style transfer that visualizes the AI's feeling. The session covers how the emotion controls the style transfer, the in-depth explanation of the style transfer model, and how it is implemented in the game. The character AI documents what it sees along its journey in the form of painting and uses style transfer to visualize its feeling to the player, allowing a new kind of player-AI interaction in the game. The character can also use style blending and region masking to focus on a particular aspect of the paintings according to its interests.

Did you know free users get access to 30% of content from the last 2 years?

Get your team full access to the most up to date GDC content

  • Game Developers Conference 2022
  • Edgar Handy
  • SQUARE ENIX CO., LTD, AI Division
  • free content
  • Machine Learning Summit
  • Programming