Inferring the Future by Imagining the Past
This work addresses a cognitive science challenge in theory of mind, offering a computational model for rapid and flexible human-like inference, though it is incremental as it builds on existing cognitive science and computer graphics ideas.
The paper tackles the problem of modeling how humans infer complex sequences of past and future events from static snapshots of dynamic scenes, and presents a Monte Carlo algorithm that correlates well with human intuitions across various domains using a small number of samples.
A single panel of a comic book can say a lot: it can depict not only where the characters currently are, but also their motions, their motivations, their emotions, and what they might do next. More generally, humans routinely infer complex sequences of past and future events from a *static snapshot* of a *dynamic scene*, even in situations they have never seen before. In this paper, we model how humans make such rapid and flexible inferences. Building on a long line of work in cognitive science, we offer a Monte Carlo algorithm whose inferences correlate well with human intuitions in a wide variety of domains, while only using a small, cognitively-plausible number of samples. Our key technical insight is a surprising connection between our inference problem and Monte Carlo path tracing, which allows us to apply decades of ideas from the computer graphics community to this seemingly-unrelated theory of mind task.