fog: Expressing Motion and Emotion through Function Composition of AI-Generated Code
For animators and designers, fog provides a novel framework to create open-ended motion vocabulary with improved semantic recognition and user control.
The paper introduces fog, a function composition framework for AI-generated code that enables expressive motion and emotion in animations. In perceptual evaluations, fog-generated animations achieved 68% recognition accuracy, a 2.68x improvement over chance, and a user study showed it supports rapid iteration and exploration.
Motion and emotion are core parts of intelligent, expressive behavior. In this paper, we introduce fog, a function composition framework for implementing and compose motion functions. We demonstrate how fog can be used to express motion and emotion in Heider-Simmel style animations. This code generation framework can help users generate functions for verbs, adverbs, gestures, and emotions to create an open-ended motion vocabulary. It is complemented by an animation editor that helps users refine motion through direct manipulation and dynamically generated UI. We evaluate our approach with a perceptual evaluation, where we test 452 fog-generated animations to see if people can recognize the semantic meaning of the motion. We find that fog's motion functions can be recognized at 68% accuracy, a 2.68x improvement over a chance baseline. In a mixed-methods user study with professionals and novices, we show that fog in interface form can support users with more rapid iteration, exploration, and control.