An improved approximate k-nearest neighbors nonlocal-means denoising method with GPU acceleration

Authors:
Wenchao Jin;Jinqing Qi
Affiliations:
School of Information and Communication Engineering, Dalian University of Technology, Dalian, China;School of Information and Communication Engineering, Dalian University of Technology, Dalian, China
Venue:
IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Year:
2012

Citing 5
Cited 0

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
An Efficient Fine-grained Parallel Genetic Algorithm Based on GPU-Accelerated

NPC '07 Proceedings of the 2007 IFIP International Conference on Network and Parallel Computing Workshops
Nonlocal Image and Movie Denoising

International Journal of Computer Vision
PatchMatch: a randomized correspondence algorithm for structural image editing

ACM SIGGRAPH 2009 papers
A high-quality video denoising algorithm based on reliable motion estimation

ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

The nonlocal-means(NLM) is a denoising algorithm which takes advantage of the redundancy of similar patches in the image. While producing state-of-the-art denoising results, the NLM algorithm has high computational complexity. In [1] Ce Liu etal. introduced approximate K-nearest neighbors(AKNN) matching to classical NLM for reducing the complexity of the algorithm. In this paper an improved AKNN-NLM algorithm with NVIDIA GPU acceleration is proposed. The experiments show that the improved GPU based AKNN-NLM algorithm have excellent performance on both image and video denoising. The GPU based implementation is up to 40 times faster than the CPU counterparts.