Mixed-Resolution Patch-Matching

Harshit Sureka, P. J. Narayanan
Centre for Visual Information Technology (CVIT)
12th European Conference on Computer Vision (ECCV), 2012


   title={Mixed-Resolution Patch-Matching},

   author={Sureka, Harshit and Narayanan, P. J.},



Download Download (PDF)   View View   Source Source   



Matching patches of a source image with patches of itself or a target image is a first step for many operations. Finding the optimum nearest-neighbors of each patch using a global search of the image is expensive. Optimality is often sacrificed for speed as a result. We present the Mixed-Resolution Patch-Matching (MRPM) algorithm that uses a pyramid representation to perform fast global search. We compare mixed- resolution patches at coarser pyramid levels to alleviate the ects of smoothing. We store more matches at coarser resolutions to ensure wider search ranges and better accuracy at finer levels. Our method achieves near optimality in terms of average error compared to exhaustive search. Our approach is simple compared to complex trees or hash tables used by others. This enables fast parallel implementations on the GPU, yielding upto 70x speedup compared to other iterative approaches. Our approach is best suited when multiple, global matches are needed.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: