2022/04/26 by Kartik Chandra, Tzu-Mao Li, Joshua Tenenbaum +1 · 1 voice · 2 citations
Computer Science · #cs.AI #cs.GR #cs.LG
paper · pdf · doi:10.1145/3528233.3530715
9 pages; 3 figures; SIGGRAPH '22 Conference Proceedings
arxiv created 2022/04/26 · arxiv published 2022/04/26 · arxiv updated 2022/04/27
We design new visual illusions by finding "adversarial examples" for principled models of human perception -- specifically, for probabilistic models, which treat vision as Bayesian inference. To perform this search efficiently, we design a differentiable probabilistic programming language, whose API exposes MCMC inference as a first-class differentiable function. We demonstrate our method by automatically creating illusions for three features of human vision: color constancy, size constancy, and face perception.