Inferring the Future by Imagining the Past

TL;DR

This paper presents a Monte Carlo algorithm inspired by computer graphics to model how humans infer past and future events from static images, aligning well with human intuition across various domains.

Contribution

It introduces a novel Monte Carlo inference method based on path tracing concepts, bridging cognitive science and computer graphics to explain human scene understanding.

Findings

Algorithm correlates with human judgments across domains

Uses a small, cognitively plausible number of samples

Connects Monte Carlo path tracing with theory of mind inference

Abstract

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.