Structure and motion from scene registration
We propose a method for estimating the 3D structure and the dense 3D motion (scene flow) of a dynamic nonrigid 3D scene, using a camera array. The core idea is to use a dense multi-camera array to construct a novel, dense 3D volumetric representation of the 3D space where each voxel holds an estimat...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2014
|
| Online Access: | http://hdl.handle.net/1721.1/90384 https://orcid.org/0000-0003-0212-5643 |
| _version_ | 1811086715045019648 |
|---|---|
| author | Basha, Tali Avidan, Shai Hornung, Alexander Matusik, Wojciech |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Basha, Tali Avidan, Shai Hornung, Alexander Matusik, Wojciech |
| author_sort | Basha, Tali |
| collection | MIT |
| description | We propose a method for estimating the 3D structure and the dense 3D motion (scene flow) of a dynamic nonrigid 3D scene, using a camera array. The core idea is to use a dense multi-camera array to construct a novel, dense 3D volumetric representation of the 3D space where each voxel holds an estimated intensity value and a confidence measure of this value. The problem of 3D structure and 3D motion estimation of a scene is thus reduced to a nonrigid registration of two volumes - hence the term ”Scene Registration”. Registering two dense 3D scalar volumes does not require recovering the 3D structure of the scene as a preprocessing step, nor does it require explicit reasoning about occlusions. From this nonrigid registration we accurately extract the 3D scene flow and the 3D structure of the scene, and successfully recover the sharp discontinuities in both time and space. We demonstrate the advantages of our method on a number of challenging synthetic and real data sets. |
| first_indexed | 2024-09-23T13:32:11Z |
| format | Article |
| id | mit-1721.1/90384 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:32:11Z |
| publishDate | 2014 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/903842022-09-28T14:37:05Z Structure and motion from scene registration Basha, Tali Avidan, Shai Hornung, Alexander Matusik, Wojciech Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Matusik, Wojciech We propose a method for estimating the 3D structure and the dense 3D motion (scene flow) of a dynamic nonrigid 3D scene, using a camera array. The core idea is to use a dense multi-camera array to construct a novel, dense 3D volumetric representation of the 3D space where each voxel holds an estimated intensity value and a confidence measure of this value. The problem of 3D structure and 3D motion estimation of a scene is thus reduced to a nonrigid registration of two volumes - hence the term ”Scene Registration”. Registering two dense 3D scalar volumes does not require recovering the 3D structure of the scene as a preprocessing step, nor does it require explicit reasoning about occlusions. From this nonrigid registration we accurately extract the 3D scene flow and the 3D structure of the scene, and successfully recover the sharp discontinuities in both time and space. We demonstrate the advantages of our method on a number of challenging synthetic and real data sets. 2014-09-26T13:50:25Z 2014-09-26T13:50:25Z 2012-06 Article http://purl.org/eprint/type/ConferencePaper 978-1-4673-1228-8 978-1-4673-1226-4 978-1-4673-1227-1 1063-6919 http://hdl.handle.net/1721.1/90384 Basha, T., S. Avidan, A. Hornung, and W. Matusik. “Structure and Motion from Scene Registration.” 2012 IEEE Conference on Computer Vision and Pattern Recognition (June 2012). https://orcid.org/0000-0003-0212-5643 en_US http://dx.doi.org/10.1109/CVPR.2012.6247830 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Basha, Tali Avidan, Shai Hornung, Alexander Matusik, Wojciech Structure and motion from scene registration |
| title | Structure and motion from scene registration |
| title_full | Structure and motion from scene registration |
| title_fullStr | Structure and motion from scene registration |
| title_full_unstemmed | Structure and motion from scene registration |
| title_short | Structure and motion from scene registration |
| title_sort | structure and motion from scene registration |
| url | http://hdl.handle.net/1721.1/90384 https://orcid.org/0000-0003-0212-5643 |
| work_keys_str_mv | AT bashatali structureandmotionfromsceneregistration AT avidanshai structureandmotionfromsceneregistration AT hornungalexander structureandmotionfromsceneregistration AT matusikwojciech structureandmotionfromsceneregistration |