Global stereo reconstruction under second order smoothness priors
Second-order priors on the smoothness of 3D surfaces are a better model of typical scenes than first-order priors. However, stereo reconstruction using global inference algorithms, such as graph-cuts, has not been able to incorporate second-order priors because the triple cliques needed to express t...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2008
|
| _version_ | 1826315013767299072 |
|---|---|
| author | Woodford, OJ Torr, PHS Reid, ID Fitzgibbon, AW |
| author_facet | Woodford, OJ Torr, PHS Reid, ID Fitzgibbon, AW |
| author_sort | Woodford, OJ |
| collection | OXFORD |
| description | Second-order priors on the smoothness of 3D surfaces are a better model of typical scenes than first-order priors. However, stereo reconstruction using global inference algorithms, such as graph-cuts, has not been able to incorporate second-order priors because the triple cliques needed to express them yield intractable (non-submodular) optimization problems.
<br>
This paper shows that inference with triple cliques can be effectively optimized. Our optimization strategy is a development of recent extensions to α-expansion, based on the “QPBO” algorithm [5, 14, 26]. The strategy is to repeatedly merge proposal depth maps using a novel extension of QPBO. Proposal depth maps can come from any source, for example fronto-parallel planes as in α-expansion, or indeed any existing stereo algorithm, with arbitrary parameter settings.
<br>
Experimental results demonstrate the usefulness of the second-order prior and the efficacy of our optimization framework. An implementation of our stereo framework is available online [34]. |
| first_indexed | 2024-12-09T03:16:37Z |
| format | Conference item |
| id | oxford-uuid:55aae210-57e2-47aa-acb0-5ff74919aa56 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-12-09T03:16:37Z |
| publishDate | 2008 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:55aae210-57e2-47aa-acb0-5ff74919aa562024-10-24T15:45:28ZGlobal stereo reconstruction under second order smoothness priorsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:55aae210-57e2-47aa-acb0-5ff74919aa56EnglishSymplectic ElementsIEEE2008Woodford, OJTorr, PHSReid, IDFitzgibbon, AWSecond-order priors on the smoothness of 3D surfaces are a better model of typical scenes than first-order priors. However, stereo reconstruction using global inference algorithms, such as graph-cuts, has not been able to incorporate second-order priors because the triple cliques needed to express them yield intractable (non-submodular) optimization problems. <br> This paper shows that inference with triple cliques can be effectively optimized. Our optimization strategy is a development of recent extensions to α-expansion, based on the “QPBO” algorithm [5, 14, 26]. The strategy is to repeatedly merge proposal depth maps using a novel extension of QPBO. Proposal depth maps can come from any source, for example fronto-parallel planes as in α-expansion, or indeed any existing stereo algorithm, with arbitrary parameter settings. <br> Experimental results demonstrate the usefulness of the second-order prior and the efficacy of our optimization framework. An implementation of our stereo framework is available online [34]. |
| spellingShingle | Woodford, OJ Torr, PHS Reid, ID Fitzgibbon, AW Global stereo reconstruction under second order smoothness priors |
| title | Global stereo reconstruction under second order smoothness priors |
| title_full | Global stereo reconstruction under second order smoothness priors |
| title_fullStr | Global stereo reconstruction under second order smoothness priors |
| title_full_unstemmed | Global stereo reconstruction under second order smoothness priors |
| title_short | Global stereo reconstruction under second order smoothness priors |
| title_sort | global stereo reconstruction under second order smoothness priors |
| work_keys_str_mv | AT woodfordoj globalstereoreconstructionundersecondordersmoothnesspriors AT torrphs globalstereoreconstructionundersecondordersmoothnesspriors AT reidid globalstereoreconstructionundersecondordersmoothnesspriors AT fitzgibbonaw globalstereoreconstructionundersecondordersmoothnesspriors |