1. [Publications](/index.php/publications)
2. On Nearest Neighbors in Non Local Means Denoising
 
 # On Nearest Neighbors in Non Local Means Denoising

  ![](/sites/default/files/styles/wide/public/publications/Slide1_1.PNG?itok=0bme7lZq)

 To denoise a reference patch, the Non-Local-Means denoising filter processes a set of neighbor patches. Few Nearest Neighbors (NN) are used to limit the computational burden of the algorithm. Here we show analytically that the NN approach introduces a bias in the denoised patch, and we propose a different neighbors’ collection criterion, named Statistical NN (SNN), to alleviate this issue. Our approach outperforms the traditional one in case of both white and colored noise: fewer SNNs generate images of higher quality, at a lower computational cost.



 ## Authors



[Iuri Frosio](/index.php/person/iuri-frosio)

[Jan Kautz](/index.php/person/jan-kautz)

 

 

 ## Publication Date



Tuesday, December 5, 2017

 

 ## Published in



[Neural Information Processing Systems (NIPS) 2017 Workshop on Nearest Neighbors…](https://nn2017.mit.edu/)

 

 ## Research Area



[Computational Photography and Imaging](/index.php/research-area/computational-photography-imaging)

[Computer Vision](/index.php/research-area/computer-vision)

 

 

 ## External Links



[On Nearest Neighbors in Non Local Means Denoising](https://arxiv.org/abs/1711.07568)

 

 

 ## Uploaded Files



[OnNearestNeighborsInNonLocalMeansDenoising.pdf](https://research.nvidia.com/sites/default/files/pubs/2017-12_On-Nearest-Neighbors//OnNearestNeighborsInNonLocalMeansDenoising.pdf "Open file in new window")6.45 MB