Computational perception of physical object properties
Name
953458476-MIT.pdf
Description
Full printable version
Size
5.29 MB
Format
Adobe PDF
Checksum (MD5)
7ebd439c0a178f1ebfc5db0e7ff5673d
Author(s)
Wu, Jiajun, Ph.D. Massachusetts Institute of Technology
Advisor(s)
William T. Freeman and Joshua B. Tenenbaum.
Date Issued
2016
Publisher
Massachusetts Institute of Technology
Abstract
We study the problem of learning physical object properties from visual data. Inspired by findings in cognitive science that even infants are able to perceive a physical world full of dynamic content at a early age, we aim to build models to characterize object properties from synthetic and real-world scenes. We build a novel dataset containing over 17, 000 videos with 101 objects in a set of visually simple but physically rich scenarios. We further propose two novel models for learning physical object properties by incorporating physics simulators, either a symbolic interpreter or a mature physics engine, with deep neural nets. Our extensive evaluations demonstrate that these models can learn physical object properties well and, with a physic engine, the responses of the model positively correlate with human responses. Future research directions include incorporating the knowledge of physical object properties into the understanding of interactions among objects, scenes, and agents.
Description
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 49-50).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.
Persistent DSpace Link
