Augmenting Movies with Interactive Narrative Agent

Netflix recently released an interactive movie that brings the concept of interactive media from video games into movie form. In contrast to the passive viewing experience with conventional movies, the interaction brings viewers into the movie scenes for an immersive experience. However, existing interactive movies are still scripted. Though there have been proposals towards freeform conversational for games and agent-directed interaction, viewers are still not in control of the story development. In this project, our objective is to transform characters in a movie into interactive objects offering viewers a real interactive experience, neither pre-scripted nor pre-filmed. We will propose and develop a self-learning avatar shadowing a selected character to learn the story from the perspective of the shadowed character. We will augment a movie with the avatar to offer interaction with a character. This proof-of-concept will shed light on turning all characters alive to offer viewers unlimited interactive experience.

Faculty Supervisor:

Mea Wang

Student:

Lynshao Celina Ma

Partner:

TCL Research America

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

University of Calgary