2026-09-19T13:16:17Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1197212026-06-06T00:55:06Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Joshua B. Tenenbaum.
Ray Chaudhuri, Shraman
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2018-12-18T19:47:13Z
2018-12-18T19:47:13Z
2018
2018
http://hdl.handle.net/1721.1/119721
1078638333
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018.
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 41-43).
While state-of-the-art machine learning models can outperform humans on certain tasks, most of them generalize poorly across domains and cannot reason about complex scenes. In this paper, we attempt to resolve this shortcoming by incorporating a physics engine as a prior for scene understanding. We test our approach on two computer vision tasks -- pose estimation and object matching -- under full occlusion, and demonstrate superior performance over state-of-the-art methods. We also present a preliminary case study which demonstrates that our model is consistent with human behavior. Our work demonstrates a successful approach to a novel and challenging task, provides a general framework to infer latent factors of scene via physics simulation, and extends support for intuitive physics-based approaches for robust visual reasoning.
by Shraman Ray Chaudhuri.
M.Eng.
43 pages
eng
Massachusetts Institute of Technology
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Reasoning about objects under full occlusion
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="8ed61025-001a-41dd-8ce3-4467cfac5ded">
<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>Reasoning about objects under full occlusion</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2018</PublicationDate>
<Authors>
<Author>
<DisplayName>Ray Chaudhuri, Shraman</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>While state-of-the-art machine learning models can outperform humans on certain tasks, most of them generalize poorly across domains and cannot reason about complex scenes. In this paper, we attempt to resolve this shortcoming by incorporating a physics engine as a prior for scene understanding. We test our approach on two computer vision tasks -- pose estimation and object matching -- under full occlusion, and demonstrate superior performance over state-of-the-art methods. We also present a preliminary case study which demonstrates that our model is consistent with human behavior. Our work demonstrates a successful approach to a novel and challenging task, provides a general framework to infer latent factors of scene via physics simulation, and extends support for intuitive physics-based approaches for robust visual reasoning.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>