Combining recognition and geometry for data-driven 3D reconstruction
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2013.
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2013
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/79237 |
| _version_ | 1826193094856409088 |
|---|---|
| author | Owens, Andrew (Andrew Hale) |
| author2 | William T. Freeman and Antonio Torralba. |
| author_facet | William T. Freeman and Antonio Torralba. Owens, Andrew (Andrew Hale) |
| author_sort | Owens, Andrew (Andrew Hale) |
| collection | MIT |
| description | Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2013. |
| first_indexed | 2024-09-23T09:33:40Z |
| format | Thesis |
| id | mit-1721.1/79237 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T09:33:40Z |
| publishDate | 2013 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/792372019-04-10T15:37:20Z Combining recognition and geometry for data-driven 3D reconstruction Owens, Andrew (Andrew Hale) William T. Freeman and Antonio Torralba. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Electrical Engineering and Computer Science. Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2013. Cataloged from PDF version of thesis. Includes bibliographical references (p. 47-50). Today's multi-view 3D reconstruction techniques rely almost exclusively on depth cues that come from multiple view geometry. While these cues can be used to produce highly accurate reconstructions, the resulting point clouds are often noisy and incomplete. Due to these issues, it may also be difficult to answer higher-level questions about the geometry, such as whether two surfaces meet at a right angle or whether a surface is planar. Furthermore, state-of-the-art reconstruction techniques generally cannot learn from training data, so having the ground-truth geometry for one scene does not aid in reconstructing similar scenes. In this work, we make two contributions toward data-driven 3D reconstruction. First, we present a dataset containing hundreds of RGBD videos that can be used as a source of training data for reconstruction algorithms. Second, we introduce the concept of the Shape Anchor, a region for which the combination of recognition and multiple view geometry allows us to accurately predict the latent, dense point cloud. We propose a technique to detect these regions and to predict their shapes, and we demonstrate it on our dataset. by Andrew Owens. S.M. 2013-06-17T19:49:43Z 2013-06-17T19:49:43Z 2013 2013 Thesis http://hdl.handle.net/1721.1/79237 845314831 eng 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 50 p. application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Owens, Andrew (Andrew Hale) Combining recognition and geometry for data-driven 3D reconstruction |
| title | Combining recognition and geometry for data-driven 3D reconstruction |
| title_full | Combining recognition and geometry for data-driven 3D reconstruction |
| title_fullStr | Combining recognition and geometry for data-driven 3D reconstruction |
| title_full_unstemmed | Combining recognition and geometry for data-driven 3D reconstruction |
| title_short | Combining recognition and geometry for data-driven 3D reconstruction |
| title_sort | combining recognition and geometry for data driven 3d reconstruction |
| topic | Electrical Engineering and Computer Science. |
| url | http://hdl.handle.net/1721.1/79237 |
| work_keys_str_mv | AT owensandrewandrewhale combiningrecognitionandgeometryfordatadriven3dreconstruction |