Show simple item record

dc.contributor.advisorWilliam Freeman
dc.contributor.authorFreeman, William T.en_US
dc.contributor.authorTorralba, Antonioen_US
dc.contributor.authorYuen, Jennyen_US
dc.contributor.authorLiu, Ceen_US
dc.contributor.otherVisionen
dc.date.accessioned2010-05-13T19:30:03Z
dc.date.available2010-05-13T19:30:03Z
dc.date.issued2010-05-08
dc.identifier.urihttp://hdl.handle.net/1721.1/54787
dc.description.abstractWhile image alignment has been studied in different areas of computer vision for decades, aligning images depicting different scenes remains a challenging problem. Analogous to optical flow where an image is aligned to its temporally adjacent frame, we propose SIFT flow, a method to align an image to its nearest neighbors in a large image corpus containing a variety of scenes. The SIFT flow algorithm consists of matching densely sampled, pixel-wise SIFT features between two images, while preserving spatial discontinuities. The SIFT features allow robust matching across different scene/object appearances, whereas the discontinuity-preserving spatial model allows matching of objects located at different parts of the scene. Experiments show that the proposed approach robustly aligns complex scene pairs containing significant spatial differences. Based on SIFT flow, we propose an alignment-based large database framework for image analysis and synthesis, where image information is transferred from the nearest neighbors to a query image according to the dense scene correspondence. This framework is demonstrated through concrete applications, such as motion field prediction from a single image, motion synthesis via object transfer, satellite image registration and face recognition.en_US
dc.format.extent17 p.en_US
dc.relation.ispartofseriesMIT-CSAIL-TR-2010-024
dc.titleSIFT Flow: Dense Correspondence across Scenes and its Applicationsen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record