eprintid: 1468724 rev_number: 45 eprint_status: archive userid: 608 dir: disk0/01/46/87/24 datestamp: 2017-06-05 11:29:10 lastmod: 2021-11-15 01:55:17 status_changed: 2017-06-05 11:29:10 type: proceedings_section metadata_visibility: show item_issues_count: 0 creators_name: Turmukhambetov, D creators_name: Campbell, NDF creators_name: Prince, SJD creators_name: Kautz, J title: Modeling Object Appearance using Context-Conditioned Component Analysis ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 keywords: Visualization, Mathematical model, Context, Context modeling, Active appearance model, Image color analysis, Analytical models note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: Subspace models have been very successful at modeling the appearance of structured image datasets when the visual objects have been aligned in the images (e.g., faces). Even with extensions that allow for global transformations or dense warps of the image, the set of visual objects whose appearance may be modeled by such methods is limited. They are unable to account for visual objects where occlusion leads to changing visibility of different object parts (without a strict layered structure) and where a one-toone mapping between parts is not preserved. For example bunches of bananas contain different numbers of bananas but each individual banana shares an appearance subspace. In this work we remove the image space alignment limitations of existing subspace models by conditioning the models on a shape dependent context that allows for the complex, non-linear structure of the appearance of the visual object to be captured and shared. This allows us to exploit the advantages of subspace appearance models with non-rigid, deformable objects whilst also dealing with complex occlusions and varying numbers of parts. We demonstrate the effectiveness of our new model with examples of structured inpainting and appearance transfer. date: 2015-10-15 date_type: published publisher: IEEE official_url: http://dx.doi.org/10.1109/CVPR.2015.7299043 vfaculties: VENG oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_source: Manually entered elements_id: 1031953 doi: 10.1109/CVPR.2015.7299043 lyricists_name: Campbell, Neill lyricists_name: Turmukhambetov, Daniyar lyricists_id: NCAMP92 lyricists_id: DTURM49 actors_name: Turmukhambetov, Daniyar actors_id: DTURM49 actors_role: owner full_text_status: public series: IEEE Conference on Computer Vision and Pattern Recognition publication: 2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) volume: 2015 place_of_pub: Boston, MA, USA pagerange: 4156-4164 pages: 9 event_title: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, United States, 7-12 June 2015 event_location: Boston, MA event_dates: 07 June 2015 - 12 June 2015 issn: 1063-6919 book_title: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference citation: Turmukhambetov, D; Campbell, NDF; Prince, SJD; Kautz, J; (2015) Modeling Object Appearance using Context-Conditioned Component Analysis. In: Proceedings of Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference. (pp. pp. 4156-4164). IEEE: Boston, MA, USA. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/1468724/1/2198.pdf