ROAM: a rich object appearance model with application to rotoscoping
Rotoscoping, the detailed delineation of scene elements through a video shot, is a painstaking task of tremendous importance in professional post-production pipelines. While pixel-wise segmentation techniques can help for this task, professional rotoscoping tools rely on parametric curves that offer...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Published: |
IEEE
2017
|
| _version_ | 1826273472070811648 |
|---|---|
| author | Miksik, O Perez-Rua, J Torr, P Perez, P |
| author_facet | Miksik, O Perez-Rua, J Torr, P Perez, P |
| author_sort | Miksik, O |
| collection | OXFORD |
| description | Rotoscoping, the detailed delineation of scene elements through a video shot, is a painstaking task of tremendous importance in professional post-production pipelines. While pixel-wise segmentation techniques can help for this task, professional rotoscoping tools rely on parametric curves that offer the artists a much better interactive control on the definition, editing and manipulation of the segments of interest. Sticking to this prevalent rotoscoping paradigm, we propose a novel framework to capture and track the visual aspect of an arbitrary object in a scene, given a first closed outline of this object. This model combines a collection of local foreground/background appearance models spread along the outline, a global appearance model of the enclosed object and a set of distinctive foreground landmarks. The structure of this rich appearance model allows simple initialization, efficient iterative optimization with exact minimization at each step, and on-line adaptation in videos. We demonstrate qualitatively and quantitatively the merit of this framework through comparisons with tools based on either dynamic segmentation with a closed curve or pixel-wise binary labelling. |
| first_indexed | 2024-03-06T22:28:41Z |
| format | Conference item |
| id | oxford-uuid:5789e127-c461-4197-9010-004b36a1c55b |
| institution | University of Oxford |
| last_indexed | 2024-03-06T22:28:41Z |
| publishDate | 2017 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:5789e127-c461-4197-9010-004b36a1c55b2022-03-26T16:57:22ZROAM: a rich object appearance model with application to rotoscopingConference itemhttp://purl.org/coar/resource_type/c_5794uuid:5789e127-c461-4197-9010-004b36a1c55bSymplectic Elements at OxfordIEEE2017Miksik, OPerez-Rua, JTorr, PPerez, PRotoscoping, the detailed delineation of scene elements through a video shot, is a painstaking task of tremendous importance in professional post-production pipelines. While pixel-wise segmentation techniques can help for this task, professional rotoscoping tools rely on parametric curves that offer the artists a much better interactive control on the definition, editing and manipulation of the segments of interest. Sticking to this prevalent rotoscoping paradigm, we propose a novel framework to capture and track the visual aspect of an arbitrary object in a scene, given a first closed outline of this object. This model combines a collection of local foreground/background appearance models spread along the outline, a global appearance model of the enclosed object and a set of distinctive foreground landmarks. The structure of this rich appearance model allows simple initialization, efficient iterative optimization with exact minimization at each step, and on-line adaptation in videos. We demonstrate qualitatively and quantitatively the merit of this framework through comparisons with tools based on either dynamic segmentation with a closed curve or pixel-wise binary labelling. |
| spellingShingle | Miksik, O Perez-Rua, J Torr, P Perez, P ROAM: a rich object appearance model with application to rotoscoping |
| title | ROAM: a rich object appearance model with application to rotoscoping |
| title_full | ROAM: a rich object appearance model with application to rotoscoping |
| title_fullStr | ROAM: a rich object appearance model with application to rotoscoping |
| title_full_unstemmed | ROAM: a rich object appearance model with application to rotoscoping |
| title_short | ROAM: a rich object appearance model with application to rotoscoping |
| title_sort | roam a rich object appearance model with application to rotoscoping |
| work_keys_str_mv | AT miksiko roamarichobjectappearancemodelwithapplicationtorotoscoping AT perezruaj roamarichobjectappearancemodelwithapplicationtorotoscoping AT torrp roamarichobjectappearancemodelwithapplicationtorotoscoping AT perezp roamarichobjectappearancemodelwithapplicationtorotoscoping |