100+Times FasterWeighted Median Filter (WMF)
Refereed conference paper presented and published in conference proceedings

Times Cited
Web of Science110WOS source URL (as at 10/05/2021) Click here for the latest count
Altmetrics Information

Other information
AbstractWeighted median, in the form of either solver or filter, has been employed in a wide range of computer vision solutions for its beneficial properties in sparsity representation. But it is hard to be accelerated due to the spatially varying weight and the median property. We propose a few efficient schemes to reduce computation complexity from O(r(2)) to O(r) where r is the kernel size. Our contribution is on a new joint-histogram representation, median tracking, and a new data structure that enables fast data access. The effectiveness of these schemes is demonstrated on optical flow estimation, stereo matching, structure-texture separation, image filtering, to name a few. The running time is largely shortened from several minutes to less than 1 second. The source code is provided in the project website.
All Author(s) ListZhang Q, Xu L, Jia JY
Name of Conference27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Start Date of Conference23/06/2014
End Date of Conference28/06/2014
Place of ConferenceColumbus
Country/Region of ConferenceUnited States of America
Detailed descriptionIEEE
Pages2830 - 2837
LanguagesEnglish-United Kingdom
Web of Science Subject CategoriesComputer Science; Computer Science, Artificial Intelligence

Last updated on 2021-11-05 at 00:36