Please use this identifier to cite or link to this item: https://doi.org/10.1109/CVPR.2013.155
DC FieldValue
dc.titleFramebreak: Dramatic image extrapolation by guided shift-maps
dc.contributor.authorZhang, Y.
dc.contributor.authorXiao, J.
dc.contributor.authorHays, J.
dc.contributor.authorTan, P.
dc.date.accessioned2014-06-19T03:11:22Z
dc.date.available2014-06-19T03:11:22Z
dc.date.issued2013
dc.identifier.citationZhang, Y., Xiao, J., Hays, J., Tan, P. (2013). Framebreak: Dramatic image extrapolation by guided shift-maps. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 1171-1178. ScholarBank@NUS Repository. https://doi.org/10.1109/CVPR.2013.155
dc.identifier.issn10636919
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/70370
dc.description.abstractWe significantly extrapolate the field of view of a photograph by learning from a roughly aligned, wide-angle guide image of the same scene category. Our method can extrapolate typical photos into complete panoramas. The extrapolation problem is formulated in the shift-map image synthesis framework. We analyze the self-similarity of the guide image to generate a set of allowable local transformations and apply them to the input image. Our guided shift-map method reserves to the scene layout of the guide image when extrapolating a photograph. While conventional shift-map methods only support translations, this is not expressive enough to characterize the self-similarity of complex scenes. Therefore we additionally allow image transformations of rotation, scaling and reflection. To handle this increase in complexity, we introduce a hierarchical graph optimization method to choose the optimal transformation at each output pixel. We demonstrate our approach on a variety of indoor, outdoor, natural, and man-made scenes. © 2013 IEEE.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/CVPR.2013.155
dc.sourceScopus
dc.subjectguided shift-map
dc.subjectimage extrapolation
dc.subjectpanorama
dc.typeConference Paper
dc.contributor.departmentELECTRICAL & COMPUTER ENGINEERING
dc.description.doi10.1109/CVPR.2013.155
dc.description.sourcetitleProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
dc.description.page1171-1178
dc.description.codenPIVRE
dc.identifier.isiut000331094301029
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.