Approximate nearest neighbor fields in video

Nir Ben-Zrihem; Lihi Zelnik-Manor

doi:https://doi.org/10.1109/CVPR.2015.7299160

Approximate nearest neighbor fields in video

Nir Ben-Zrihem, Lihi Zelnik-Manor

Technion - Israel Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We introduce RIANN (Ring Intersection Approximate Nearest Neighbor search), an algorithm for matching patches of a video to a set of reference patches in real-time. For each query, RIANN finds potential matches by intersecting rings around key points in appearance space. Its search complexity is reversely correlated to the amount of temporal change, making it a good fit for videos, where typically most patches change slowly with time. Experiments show that RIANN is up to two orders of magnitude faster than previous ANN methods, and is the only solution that operates in real-time. We further demonstrate how RIANN can be used for real-time video processing and provide examples for a range of real-time video applications, including colorization, denoising, and several artistic effects.

Original language	English
Title of host publication	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Pages	5233-5242
Number of pages	10
ISBN (Electronic)	9781467369640
DOIs	https://doi.org/10.1109/CVPR.2015.7299160
State	Published - 14 Oct 2015
Event	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States Duration: 7 Jun 2015 → 12 Jun 2015

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	07-12-June-2015

Conference

Conference	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Country/Territory	United States
City	Boston
Period	7/06/15 → 12/06/15

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition

Access to Document

https://doi.org/10.1109/CVPR.2015.7299160

Cite this

@inproceedings{af43cef11daf4bc5b9772889e2248658,

title = "Approximate nearest neighbor fields in video",

abstract = "We introduce RIANN (Ring Intersection Approximate Nearest Neighbor search), an algorithm for matching patches of a video to a set of reference patches in real-time. For each query, RIANN finds potential matches by intersecting rings around key points in appearance space. Its search complexity is reversely correlated to the amount of temporal change, making it a good fit for videos, where typically most patches change slowly with time. Experiments show that RIANN is up to two orders of magnitude faster than previous ANN methods, and is the only solution that operates in real-time. We further demonstrate how RIANN can be used for real-time video processing and provide examples for a range of real-time video applications, including colorization, denoising, and several artistic effects.",

author = "Nir Ben-Zrihem and Lihi Zelnik-Manor",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 ; Conference date: 07-06-2015 Through 12-06-2015",

year = "2015",

month = oct,

day = "14",

doi = "https://doi.org/10.1109/CVPR.2015.7299160",

language = "الإنجليزيّة",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

pages = "5233--5242",

booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",

}

Ben-Zrihem, N & Zelnik-Manor, L 2015, Approximate nearest neighbor fields in video. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015., 7299160, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, pp. 5233-5242, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 7/06/15. https://doi.org/10.1109/CVPR.2015.7299160

Approximate nearest neighbor fields in video. / Ben-Zrihem, Nir; Zelnik-Manor, Lihi.
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. 2015. p. 5233-5242 7299160 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Approximate nearest neighbor fields in video

AU - Ben-Zrihem, Nir

AU - Zelnik-Manor, Lihi

PY - 2015/10/14

Y1 - 2015/10/14

N2 - We introduce RIANN (Ring Intersection Approximate Nearest Neighbor search), an algorithm for matching patches of a video to a set of reference patches in real-time. For each query, RIANN finds potential matches by intersecting rings around key points in appearance space. Its search complexity is reversely correlated to the amount of temporal change, making it a good fit for videos, where typically most patches change slowly with time. Experiments show that RIANN is up to two orders of magnitude faster than previous ANN methods, and is the only solution that operates in real-time. We further demonstrate how RIANN can be used for real-time video processing and provide examples for a range of real-time video applications, including colorization, denoising, and several artistic effects.

AB - We introduce RIANN (Ring Intersection Approximate Nearest Neighbor search), an algorithm for matching patches of a video to a set of reference patches in real-time. For each query, RIANN finds potential matches by intersecting rings around key points in appearance space. Its search complexity is reversely correlated to the amount of temporal change, making it a good fit for videos, where typically most patches change slowly with time. Experiments show that RIANN is up to two orders of magnitude faster than previous ANN methods, and is the only solution that operates in real-time. We further demonstrate how RIANN can be used for real-time video processing and provide examples for a range of real-time video applications, including colorization, denoising, and several artistic effects.

UR - http://www.scopus.com/inward/record.url?scp=84959208891&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/CVPR.2015.7299160

DO - https://doi.org/10.1109/CVPR.2015.7299160

M3 - منشور من مؤتمر

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 5233

EP - 5242

BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

T2 - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

Y2 - 7 June 2015 through 12 June 2015

ER -

Approximate nearest neighbor fields in video

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this