Mixed-Resolution Patch-Matching
Abstract
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 effects 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 70× speedup compared to other iterative approaches. Our approach is best suited when multiple, global matches are needed.
Cite
Text
Sureka and Narayanan. "Mixed-Resolution Patch-Matching." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33783-3_14Markdown
[Sureka and Narayanan. "Mixed-Resolution Patch-Matching." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/sureka2012eccv-mixed/) doi:10.1007/978-3-642-33783-3_14BibTeX
@inproceedings{sureka2012eccv-mixed,
title = {{Mixed-Resolution Patch-Matching}},
author = {Sureka, Harshit and Narayanan, P. J.},
booktitle = {European Conference on Computer Vision},
year = {2012},
pages = {187-198},
doi = {10.1007/978-3-642-33783-3_14},
url = {https://mlanthology.org/eccv/2012/sureka2012eccv-mixed/}
}