Approximate nearest neighbors: towards removing the curse of dimensionality
STOC '98 Proceedings of the thirtieth annual ACM symposium on Theory of computing
An optimal algorithm for approximate nearest neighbor searching fixed dimensions
Journal of the ACM (JACM)
Fast texture synthesis using tree-structured vector quantization
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
I3D '01 Proceedings of the 2001 symposium on Interactive 3D graphics
Synthesis of bidirectional texture functions on arbitrary surfaces
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Texture Synthesis by Non-Parametric Sampling
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
A Non-Local Algorithm for Image Denoising
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
What Is a Good Nearest Neighbors Algorithm for Finding Similar Patches in Images?
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
PatchMatch: a randomized correspondence algorithm for structural image editing
ACM SIGGRAPH 2009 papers
The generalized patchmatch correspondence algorithm
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Fast Exact Nearest Patch Matching for Patch-Based Image Editing and Processing
IEEE Transactions on Visualization and Computer Graphics
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Hi-index | 0.00 |
TreeCANN is a fast algorithm for approximately matching all patches between two images. It does so by following the established convention of finding an initial set of matching patch candidates between the two images and then propagating good matches to neighboring patches in the image plane. TreeCANN accelerates each of these components substantially leading to an algorithm that is ×3 to ×5 faster than existing methods. Seed matching is achieved using a properly tuned k-d tree on a sparse grid of patches. In particular, we show that a sequence of key design decisions can make k-d trees run as fast as recently proposed state-of-the-art methods, and because of image coherency it is enough to consider only a sparse grid of patches across the image plane. We then develop a novel propagation step that is based on the integral image, which drastically reduces the computational load that is dominated by the need to repeatedly measure similarity between pairs of patches. As a by-product we give an optimal algorithm for exact matching that is based on the integral image. The proposed exact algorithm is faster than previously reported results and depends only on the size of the images and not on the size of the patches. We report results on large and varied data sets and show that TreeCANN is orders of magnitude faster than exact NN search yet produces matches that are within 1% error, compared to the exact NN search.