Recovering Three-Dimensional Structure from Motion with Surface Reconstruction
We address the computational role that the construction of a complete surface representation may play in the recovery of 3--D structure from motion. We present a model that combines a feature--based structure--from- -motion algorithm with smooth surface interpolation. This model can represent...
| Main Authors: | , , , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6576 |
| _version_ | 1811082400293191680 |
|---|---|
| author | Hildreth, Ellen C. Ando, Hiroshi Anderson, Richard Treue, Stefan |
| author_facet | Hildreth, Ellen C. Ando, Hiroshi Anderson, Richard Treue, Stefan |
| author_sort | Hildreth, Ellen C. |
| collection | MIT |
| description | We address the computational role that the construction of a complete surface representation may play in the recovery of 3--D structure from motion. We present a model that combines a feature--based structure--from- -motion algorithm with smooth surface interpolation. This model can represent multiple surfaces in a given viewing direction, incorporates surface constraints from object boundaries, and groups image features using their 2--D image motion. Computer simulations relate the model's behavior to perceptual observations. In a companion paper, we discuss further perceptual experiments regarding the role of surface reconstruction in the human recovery of 3--D structure from motion. |
| first_indexed | 2024-09-23T12:02:29Z |
| id | mit-1721.1/6576 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T12:02:29Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/65762019-04-12T08:31:34Z Recovering Three-Dimensional Structure from Motion with Surface Reconstruction Hildreth, Ellen C. Ando, Hiroshi Anderson, Richard Treue, Stefan We address the computational role that the construction of a complete surface representation may play in the recovery of 3--D structure from motion. We present a model that combines a feature--based structure--from- -motion algorithm with smooth surface interpolation. This model can represent multiple surfaces in a given viewing direction, incorporates surface constraints from object boundaries, and groups image features using their 2--D image motion. Computer simulations relate the model's behavior to perceptual observations. In a companion paper, we discuss further perceptual experiments regarding the role of surface reconstruction in the human recovery of 3--D structure from motion. 2004-10-08T20:28:52Z 2004-10-08T20:28:52Z 1991-12-01 AIM-1314 http://hdl.handle.net/1721.1/6576 en_US AIM-1314 8135487 bytes 3192658 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Hildreth, Ellen C. Ando, Hiroshi Anderson, Richard Treue, Stefan Recovering Three-Dimensional Structure from Motion with Surface Reconstruction |
| title | Recovering Three-Dimensional Structure from Motion with Surface Reconstruction |
| title_full | Recovering Three-Dimensional Structure from Motion with Surface Reconstruction |
| title_fullStr | Recovering Three-Dimensional Structure from Motion with Surface Reconstruction |
| title_full_unstemmed | Recovering Three-Dimensional Structure from Motion with Surface Reconstruction |
| title_short | Recovering Three-Dimensional Structure from Motion with Surface Reconstruction |
| title_sort | recovering three dimensional structure from motion with surface reconstruction |
| url | http://hdl.handle.net/1721.1/6576 |
| work_keys_str_mv | AT hildrethellenc recoveringthreedimensionalstructurefrommotionwithsurfacereconstruction AT andohiroshi recoveringthreedimensionalstructurefrommotionwithsurfacereconstruction AT andersonrichard recoveringthreedimensionalstructurefrommotionwithsurfacereconstruction AT treuestefan recoveringthreedimensionalstructurefrommotionwithsurfacereconstruction |