Abstract | ||
---|---|---|
PatchMatch is a fast algorithm for computing dense approximate nearest neighbor correspondences between patches of two image
regions [1]. This paper generalizes PatchMatch in three ways: (1) to find k nearest neighbors, as opposed to just one, (2)
to search across scales and rotations, in addition to just translations, and (3) to match using arbitrary descriptors and
distances, not just sum-of-squared-differences on patch colors. In addition, we offer new search and parallelization strategies
that further accelerate the method, and we show performance improvements over standard kd-tree techniques across a variety
of inputs. In contrast to many previous matching algorithms, which for efficiency reasons have restricted matching to sparse
interest points, or spatially proximate matches, our algorithm can efficiently find global, dense matches, even while matching
across all scales and rotations. This is especially useful for computer vision applications, where our algorithm can be used
as an efficient general-purpose component. We explore a variety of vision applications: denoising, finding forgeries by detecting
cloned regions, symmetry detection, and object detection.
|
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/978-3-642-15558-1_3 | European Conference on Computer Vision |
Keywords | Field | DocType |
symmetry detection,arbitrary descriptors,vision application,new search,object detection,dense approximate nearest neighbor,generalized patchmatch correspondence algorithm,computer vision application,fast algorithm,dense match,previous matching algorithm,computer vision,k nearest neighbor,kd tree | Noise reduction,k-nearest neighbors algorithm,Object detection,Pattern recognition,Computer science,Best bin first,Algorithm,Nearest-neighbor chain algorithm,Artificial intelligence,Image denoising,Nearest neighbor search,Machine learning | Conference |
Volume | ISSN | ISBN |
6313 | 0302-9743 | 3-642-15557-X |
Citations | PageRank | References |
247 | 7.04 | 28 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Connelly Barnes | 1 | 1729 | 59.07 |
Eli Shechtman | 2 | 4340 | 177.94 |
Dan B. Goldman | 3 | 2321 | 85.23 |
Adam Finkelstein | 4 | 4041 | 299.42 |