Multi-view stereo via volumetric graph-cuts
This paper presents a novel formulation for the multi-view scene reconstruction problem. While this formulation benefits from a volumetric scene representation, it is amenable to a computationally tractable global optimisation using Graph-cuts. The algorithm proposed uses the visual hull of the scen...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Jezik: | English |
| Izdano: |
IEEE
2005
|
| _version_ | 1826315162910457856 |
|---|---|
| author | Vogiatzis, G Torr, PHS Cipolla, R |
| author_facet | Vogiatzis, G Torr, PHS Cipolla, R |
| author_sort | Vogiatzis, G |
| collection | OXFORD |
| description | This paper presents a novel formulation for the multi-view scene reconstruction problem. While this formulation benefits from a volumetric scene representation, it is amenable to a computationally tractable global optimisation using Graph-cuts. The algorithm proposed uses the visual hull of the scene to infer occlusions and as a constraint on the topology of the scene. A photo consistency-based surface cost functional is defined and discretised with a weighted graph. The optimal surface under this discretised functional is obtained as the minimum cut solution of the weighted graph. Our method provides a viewpoint independent surface regularisation, approximate handling of occlusions and a tractable optimisation scheme. Promising experimental results on real scenes as well as a quantitative evaluation on a synthetic scene are presented. |
| first_indexed | 2024-12-09T03:20:40Z |
| format | Conference item |
| id | oxford-uuid:bd577995-97c5-4d40-a6de-78e99318939c |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-12-09T03:20:40Z |
| publishDate | 2005 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:bd577995-97c5-4d40-a6de-78e99318939c2024-11-05T14:02:01ZMulti-view stereo via volumetric graph-cutsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:bd577995-97c5-4d40-a6de-78e99318939cEnglishSymplectic ElementsIEEE2005Vogiatzis, GTorr, PHSCipolla, RThis paper presents a novel formulation for the multi-view scene reconstruction problem. While this formulation benefits from a volumetric scene representation, it is amenable to a computationally tractable global optimisation using Graph-cuts. The algorithm proposed uses the visual hull of the scene to infer occlusions and as a constraint on the topology of the scene. A photo consistency-based surface cost functional is defined and discretised with a weighted graph. The optimal surface under this discretised functional is obtained as the minimum cut solution of the weighted graph. Our method provides a viewpoint independent surface regularisation, approximate handling of occlusions and a tractable optimisation scheme. Promising experimental results on real scenes as well as a quantitative evaluation on a synthetic scene are presented. |
| spellingShingle | Vogiatzis, G Torr, PHS Cipolla, R Multi-view stereo via volumetric graph-cuts |
| title | Multi-view stereo via volumetric graph-cuts |
| title_full | Multi-view stereo via volumetric graph-cuts |
| title_fullStr | Multi-view stereo via volumetric graph-cuts |
| title_full_unstemmed | Multi-view stereo via volumetric graph-cuts |
| title_short | Multi-view stereo via volumetric graph-cuts |
| title_sort | multi view stereo via volumetric graph cuts |
| work_keys_str_mv | AT vogiatzisg multiviewstereoviavolumetricgraphcuts AT torrphs multiviewstereoviavolumetricgraphcuts AT cipollar multiviewstereoviavolumetricgraphcuts |