2026-09-20T13:32:26Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1037362021-07-05T14:03:20Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
William T. Freeman and Joshua B. Tenenbaum.
Wu, Jiajun, Ph.D. Massachusetts Institute of Technology
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2016-07-18T20:05:15Z
2016-07-18T20:05:15Z
2016
2016
http://hdl.handle.net/1721.1/103736
953458476
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).
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.
by Jiajun Wu.
S.M.
50 pages
eng
Massachusetts Institute of Technology
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.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Computational perception of physical object properties
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="1bfd081d-5631-4058-b1e4-3f30fb74a71c">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Computational perception of physical object properties</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2016</PublicationDate>
<Authors>
<Author>
<DisplayName>Wu, Jiajun, Ph.D. Massachusetts Institute of Technology</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<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.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>