Unsupervised Discovery of 3D Physical Objects

TitleUnsupervised Discovery of 3D Physical Objects
Publication TypeConference Paper
Year of Publication2021
AuthorsDu, Y, Smith, KA, Ullman, T, Tenenbaum, JB, Wu, J
Conference NameInternational Conference on Learning Representations
Date Published07/2020
Abstract

We study the problem of unsupervised physical object discovery. Unlike existing frameworks that aim to learn to decompose scenes into 2D segments purely based on each object's appearance, we explore how physics, especially object interactions,facilitates learning to disentangle and segment instances from raw videos, and to infer the 3D geometry and position of each object, all without supervision. Drawing inspiration from developmental psychology, our Physical Object Discovery Network (POD-Net) uses both multi-scale pixel cues and physical motion cues to accurately segment observable and partially occluded objects of varying sizes, and infer properties of those objects. Our model reliably segments objects on both synthetic and real scenes. The discovered object properties can also be used to reason about physical events.

URLhttps://openreview.net/forum?id=lf7st0bJIA5

Associated Module: 

CBMM Relationship: 

  • CBMM Related