Title
"Mind the gap": tele-registration for structure-driven image completion
Abstract
Concocting a plausible composition from several non-overlapping image pieces, whose relative positions are not fixed in advance and without having the benefit of priors, can be a daunting task. Here we propose such a method, starting with a set of sloppily pasted image pieces with gaps between them. We first extract salient curves that approach the gaps from non-tangential directions, and use likely correspondences between pairs of such curves to guide a novel tele-registration method that simultaneously aligns all the pieces together. A structure-driven image completion technique is then proposed to fill the gaps, allowing the subsequent employment of standard in-painting tools to finish the job.
Year
DOI
Venue
2013
10.1145/2508363.2508373
ACM Trans. Graph.
Keywords
Field
DocType
structure-driven image completion technique,daunting task,plausible composition,extract salient curve,non-overlapping image piece,likely correspondence,sloppily pasted image piece,novel tele-registration method,relative position,non-tangential direction,stitching,texture synthesis
Computer vision,Image stitching,Computer graphics (images),Computer science,Image editing,Artificial intelligence,Prior probability,Texture synthesis,Salient
Journal
Volume
Issue
ISSN
32
6
0730-0301
Citations 
PageRank 
References 
12
0.49
27
Authors
7
Name
Order
Citations
PageRank
Hui Huang169452.19
Kangxue Yin2503.66
Minglun Gong3134085.53
Dani Lischinski45465340.85
Daniel Cohen-Or510588533.55
Uri Ascher612912.07
Baoquan Chen72095111.30