Accurate and Scalable Surface Representation and Reconstruction from Images
We introduce a new surface representation, the patchwork, to extend the problem of surface reconstruction from multiple images. A patchwork is the combination of several patches that are built one by one. This design potentially allows the reconstruction of an object of arbitrarily large dimensions...
| Autori principali: | , , , |
|---|---|
| Altri autori: | |
| Lingua: | en_US |
| Pubblicazione: |
2005
|
| Accesso online: | http://hdl.handle.net/1721.1/30586 |
| _version_ | 1826189119626149888 |
|---|---|
| author | Zeng, Gang Paris, Sylvain Quan, Long Sillion, Francois |
| author2 | Computer Graphics |
| author_facet | Computer Graphics Zeng, Gang Paris, Sylvain Quan, Long Sillion, Francois |
| author_sort | Zeng, Gang |
| collection | MIT |
| description | We introduce a new surface representation, the patchwork, to extend the problem of surface reconstruction from multiple images. A patchwork is the combination of several patches that are built one by one. This design potentially allows the reconstruction of an object of arbitrarily large dimensions while preserving a fine level of detail. We formally demonstrate that this strategy leads to a spatial complexity independent of the dimensions of the reconstructed object, and to a time complexity linear with respect to the object area. The former property ensures that we never run out of storage (memory) and the latter means that reconstructing an object can be done in a reasonable amount of time. In addition, we show that the patchwork representation handles equivalently open and closed surfaces whereas most of the existing approaches are limited to a specific scenario (open or closed surface but not both).Most of the existing optimization techniques can be cast into this framework. To illustrate the possibilities offered by this approach, we propose two applications that expose how it dramatically extends a recent accurate graph-cut technique. We first revisit the popular carving techniques. This results in a well-posed reconstruction problem that still enjoys the tractability of voxel space. We also show how we can advantageously combine several image-driven criteria to achieve a finely detailed geometry by surface propagation. The above properties of the patchwork representation and reconstruction are extensively demonstrated on real image sequences. |
| first_indexed | 2024-09-23T08:09:50Z |
| id | mit-1721.1/30586 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:09:50Z |
| publishDate | 2005 |
| record_format | dspace |
| spelling | mit-1721.1/305862019-04-09T17:03:31Z Accurate and Scalable Surface Representation and Reconstruction from Images Zeng, Gang Paris, Sylvain Quan, Long Sillion, Francois Computer Graphics We introduce a new surface representation, the patchwork, to extend the problem of surface reconstruction from multiple images. A patchwork is the combination of several patches that are built one by one. This design potentially allows the reconstruction of an object of arbitrarily large dimensions while preserving a fine level of detail. We formally demonstrate that this strategy leads to a spatial complexity independent of the dimensions of the reconstructed object, and to a time complexity linear with respect to the object area. The former property ensures that we never run out of storage (memory) and the latter means that reconstructing an object can be done in a reasonable amount of time. In addition, we show that the patchwork representation handles equivalently open and closed surfaces whereas most of the existing approaches are limited to a specific scenario (open or closed surface but not both).Most of the existing optimization techniques can be cast into this framework. To illustrate the possibilities offered by this approach, we propose two applications that expose how it dramatically extends a recent accurate graph-cut technique. We first revisit the popular carving techniques. This results in a well-posed reconstruction problem that still enjoys the tractability of voxel space. We also show how we can advantageously combine several image-driven criteria to achieve a finely detailed geometry by surface propagation. The above properties of the patchwork representation and reconstruction are extensively demonstrated on real image sequences. 2005-12-22T02:41:10Z 2005-12-22T02:41:10Z 2005-11-18 MIT-CSAIL-TR-2005-076 MIT-LCS-TR-1011 http://hdl.handle.net/1721.1/30586 en_US Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory 35 p. 126753884 bytes 4493080 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Zeng, Gang Paris, Sylvain Quan, Long Sillion, Francois Accurate and Scalable Surface Representation and Reconstruction from Images |
| title | Accurate and Scalable Surface Representation and Reconstruction from Images |
| title_full | Accurate and Scalable Surface Representation and Reconstruction from Images |
| title_fullStr | Accurate and Scalable Surface Representation and Reconstruction from Images |
| title_full_unstemmed | Accurate and Scalable Surface Representation and Reconstruction from Images |
| title_short | Accurate and Scalable Surface Representation and Reconstruction from Images |
| title_sort | accurate and scalable surface representation and reconstruction from images |
| url | http://hdl.handle.net/1721.1/30586 |
| work_keys_str_mv | AT zenggang accurateandscalablesurfacerepresentationandreconstructionfromimages AT parissylvain accurateandscalablesurfacerepresentationandreconstructionfromimages AT quanlong accurateandscalablesurfacerepresentationandreconstructionfromimages AT sillionfrancois accurateandscalablesurfacerepresentationandreconstructionfromimages |