Joint Adaptive Sparsity and Low-Rankness on the Fly

An Online Tensor Reconstruction Scheme for Video Denoising

Bihan Wen, Yanjun Li, Luke Pfister, Yoram Bresler

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recent works on adaptive sparse and low-rank signal modeling have demonstrated their usefulness, especially in image/video processing applications. While a patch-based sparse model imposes local structure, low-rankness of the grouped patches exploits non-local correlation. Applying either approach alone usually limits performance in various low-level vision tasks. In this work, we propose a novel video denoising method, based on an online tensor reconstruction scheme with a joint adaptive sparse and lowrank model, dubbed SALT. An efficient and unsupervised online unitary sparsifying transform learning method is introduced to impose adaptive sparsity on the fly. We develop an efficient 3D spatio-temporal data reconstruction framework based on the proposed online learning method, which exhibits low latency and can potentially handle streaming videos. To the best of our knowledge, this is the first work that combines adaptive sparsity and low-rankness for video denoising, and the first work of solving the proposed problem in an online fashion. We demonstrate video denoising results over commonly used videos from public datasets. Numerical experiments show that the proposed video denoising method outperforms competing methods.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages241-250
Number of pages10
ISBN (Electronic)9781538610329
DOIs
StatePublished - Dec 22 2017
Event16th IEEE International Conference on Computer Vision, ICCV 2017 - Venice, Italy
Duration: Oct 22 2017Oct 29 2017

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2017-October
ISSN (Print)1550-5499

Other

Other16th IEEE International Conference on Computer Vision, ICCV 2017
CountryItaly
CityVenice
Period10/22/1710/29/17

Fingerprint

Tensors
Video streaming
Processing
Experiments

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Wen, B., Li, Y., Pfister, L., & Bresler, Y. (2017). Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising. In Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017 (pp. 241-250). [8237297] (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2017-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2017.35

Joint Adaptive Sparsity and Low-Rankness on the Fly : An Online Tensor Reconstruction Scheme for Video Denoising. / Wen, Bihan; Li, Yanjun; Pfister, Luke; Bresler, Yoram.

Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 241-250 8237297 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2017-October).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wen, B, Li, Y, Pfister, L & Bresler, Y 2017, Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising. in Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017., 8237297, Proceedings of the IEEE International Conference on Computer Vision, vol. 2017-October, Institute of Electrical and Electronics Engineers Inc., pp. 241-250, 16th IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 10/22/17. https://doi.org/10.1109/ICCV.2017.35
Wen B, Li Y, Pfister L, Bresler Y. Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising. In Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 241-250. 8237297. (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2017.35
Wen, Bihan ; Li, Yanjun ; Pfister, Luke ; Bresler, Yoram. / Joint Adaptive Sparsity and Low-Rankness on the Fly : An Online Tensor Reconstruction Scheme for Video Denoising. Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 241-250 (Proceedings of the IEEE International Conference on Computer Vision).
@inproceedings{74404fb97e054db285477f94ee63ba78,
title = "Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising",
abstract = "Recent works on adaptive sparse and low-rank signal modeling have demonstrated their usefulness, especially in image/video processing applications. While a patch-based sparse model imposes local structure, low-rankness of the grouped patches exploits non-local correlation. Applying either approach alone usually limits performance in various low-level vision tasks. In this work, we propose a novel video denoising method, based on an online tensor reconstruction scheme with a joint adaptive sparse and lowrank model, dubbed SALT. An efficient and unsupervised online unitary sparsifying transform learning method is introduced to impose adaptive sparsity on the fly. We develop an efficient 3D spatio-temporal data reconstruction framework based on the proposed online learning method, which exhibits low latency and can potentially handle streaming videos. To the best of our knowledge, this is the first work that combines adaptive sparsity and low-rankness for video denoising, and the first work of solving the proposed problem in an online fashion. We demonstrate video denoising results over commonly used videos from public datasets. Numerical experiments show that the proposed video denoising method outperforms competing methods.",
author = "Bihan Wen and Yanjun Li and Luke Pfister and Yoram Bresler",
year = "2017",
month = "12",
day = "22",
doi = "10.1109/ICCV.2017.35",
language = "English (US)",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "241--250",
booktitle = "Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017",
address = "United States",

}

TY - GEN

T1 - Joint Adaptive Sparsity and Low-Rankness on the Fly

T2 - An Online Tensor Reconstruction Scheme for Video Denoising

AU - Wen, Bihan

AU - Li, Yanjun

AU - Pfister, Luke

AU - Bresler, Yoram

PY - 2017/12/22

Y1 - 2017/12/22

N2 - Recent works on adaptive sparse and low-rank signal modeling have demonstrated their usefulness, especially in image/video processing applications. While a patch-based sparse model imposes local structure, low-rankness of the grouped patches exploits non-local correlation. Applying either approach alone usually limits performance in various low-level vision tasks. In this work, we propose a novel video denoising method, based on an online tensor reconstruction scheme with a joint adaptive sparse and lowrank model, dubbed SALT. An efficient and unsupervised online unitary sparsifying transform learning method is introduced to impose adaptive sparsity on the fly. We develop an efficient 3D spatio-temporal data reconstruction framework based on the proposed online learning method, which exhibits low latency and can potentially handle streaming videos. To the best of our knowledge, this is the first work that combines adaptive sparsity and low-rankness for video denoising, and the first work of solving the proposed problem in an online fashion. We demonstrate video denoising results over commonly used videos from public datasets. Numerical experiments show that the proposed video denoising method outperforms competing methods.

AB - Recent works on adaptive sparse and low-rank signal modeling have demonstrated their usefulness, especially in image/video processing applications. While a patch-based sparse model imposes local structure, low-rankness of the grouped patches exploits non-local correlation. Applying either approach alone usually limits performance in various low-level vision tasks. In this work, we propose a novel video denoising method, based on an online tensor reconstruction scheme with a joint adaptive sparse and lowrank model, dubbed SALT. An efficient and unsupervised online unitary sparsifying transform learning method is introduced to impose adaptive sparsity on the fly. We develop an efficient 3D spatio-temporal data reconstruction framework based on the proposed online learning method, which exhibits low latency and can potentially handle streaming videos. To the best of our knowledge, this is the first work that combines adaptive sparsity and low-rankness for video denoising, and the first work of solving the proposed problem in an online fashion. We demonstrate video denoising results over commonly used videos from public datasets. Numerical experiments show that the proposed video denoising method outperforms competing methods.

UR - http://www.scopus.com/inward/record.url?scp=85041929338&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041929338&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2017.35

DO - 10.1109/ICCV.2017.35

M3 - Conference contribution

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 241

EP - 250

BT - Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -