Please use this identifier to cite or link to this item:
https://doi.org/10.1109/CVPR.2013.155
DC Field | Value | |
---|---|---|
dc.title | Framebreak: Dramatic image extrapolation by guided shift-maps | |
dc.contributor.author | Zhang, Y. | |
dc.contributor.author | Xiao, J. | |
dc.contributor.author | Hays, J. | |
dc.contributor.author | Tan, P. | |
dc.date.accessioned | 2014-06-19T03:11:22Z | |
dc.date.available | 2014-06-19T03:11:22Z | |
dc.date.issued | 2013 | |
dc.identifier.citation | Zhang, 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.issn | 10636919 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/70370 | |
dc.description.abstract | We 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.uri | http://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/CVPR.2013.155 | |
dc.source | Scopus | |
dc.subject | guided shift-map | |
dc.subject | image extrapolation | |
dc.subject | panorama | |
dc.type | Conference Paper | |
dc.contributor.department | ELECTRICAL & COMPUTER ENGINEERING | |
dc.description.doi | 10.1109/CVPR.2013.155 | |
dc.description.sourcetitle | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | |
dc.description.page | 1171-1178 | |
dc.description.coden | PIVRE | |
dc.identifier.isiut | 000331094301029 | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.