Title
PatchMatch: a randomized correspondence algorithm for structural image editing
Abstract
This paper presents interactive image editing tools using a new randomized algorithm for quickly finding approximate nearest-neighbor matches between image patches. Previous research in graphics and vision has leveraged such nearest-neighbor searches to provide a variety of high-level digital image editing tools. However, the cost of computing a field of such matches for an entire image has eluded previous efforts to provide interactive performance. Our algorithm offers substantial performance improvements over the previous state of the art (20-100x), enabling its use in interactive editing tools. The key insights driving the algorithm are that some good patch matches can be found via random sampling, and that natural coherence in the imagery allows us to propagate such matches quickly to surrounding areas. We offer theoretical analysis of the convergence properties of the algorithm, as well as empirical and practical evidence for its high quality and performance. This one simple algorithm forms the basis for a variety of tools -- image retargeting, completion and reshuffling -- that can be used together in the context of a high-level image editing application. Finally, we propose additional intuitive constraints on the synthesis process that offer the user a level of control unavailable in previous methods.
Year
DOI
Venue
2009
10.1145/1576246.1531330
ACM Trans. Graph.
Keywords
Field
DocType
completion,nearest neighbor search,digital image,randomized algorithm,random sampling
Convergence (routing),Computer graphics (images),Computer science,Image editing,Seam carving,Digital image,Artificial intelligence,Graphics,Randomized algorithm,Computer vision,Mathematical optimization,Algorithm,Retargeting,SIMPLE algorithm,Machine learning
Journal
Volume
Issue
ISSN
28
3
0730-0301
Citations 
PageRank 
References 
673
18.81
33
Authors
4
Search Limit
100673
Name
Order
Citations
PageRank
Connelly Barnes1172959.07
Eli Shechtman24340177.94
Adam Finkelstein34041299.42
Dan B. Goldman4232185.23