2026-09-18T22:56:22Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1197532026-06-06T00:55:50Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Jonathan P. How.
Chan, Kevin S. (Kevin Sao Wei)
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2018-12-18T19:48:35Z
2018-12-18T19:48:35Z
2018
2018
http://hdl.handle.net/1721.1/119753
1078691569
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 50-51).
Existing learned methods for monocular depth estimation use only a single view of scene for depth evaluation, so they inherently overt to their training scenes and cannot generalize well to new datasets. This thesis presents a neural network for multiview monocular depth estimation. Teaching a network to estimate depth via structure from motion allows it to generalize better to new environments with unfamiliar objects. This thesis extends recent work in unsupervised methods for single-view monocular depth estimation and uses the reconstruction losses for training posed in those works. Models and baseline models were evaluated on a variety of datasets and results indicate that indicate multiview models generalize across datasets better than previous work. This work is unique in that it emphasizes cross domain performance and ability to generalize more so than performance on the training set.
by Kevin S. Chan.
M.Eng.
51 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.
Multiview monocular depth estimation using unsupervised learning methods
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="cafc9ad1-e118-4985-80de-79987e783ddb">
<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>Multiview monocular depth estimation using unsupervised learning methods</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2018</PublicationDate>
<Authors>
<Author>
<DisplayName>Chan, Kevin S. (Kevin Sao Wei)</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>Existing learned methods for monocular depth estimation use only a single view of scene for depth evaluation, so they inherently overt to their training scenes and cannot generalize well to new datasets. This thesis presents a neural network for multiview monocular depth estimation. Teaching a network to estimate depth via structure from motion allows it to generalize better to new environments with unfamiliar objects. This thesis extends recent work in unsupervised methods for single-view monocular depth estimation and uses the reconstruction losses for training posed in those works. Models and baseline models were evaluated on a variety of datasets and results indicate that indicate multiview models generalize across datasets better than previous work. This work is unique in that it emphasizes cross domain performance and ability to generalize more so than performance on the training set.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>