=============

SALT based Video Denoising accompanies the following publication: "Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising," IEEE International Conference on Computer Vision (ICCV), 2017. ICCV 2017, PDF available

We propose a video denoising method, based on a novel Sparse And Low-rank Tensor (SALT) model. An efficient and unsupervised online unitary sparsifying transform learning method is introduced to impose adaptive sparsity on the fly. SALT based video denoising 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.

The SALT package includes (1) a collection of the SALT Matlab functions, and (2) example data used in the SALT paper.

You can download our other software packages at: Transform Learning Site.

Paper available here.

In case of use, please cite our publication:

Bihan Wen, Yanjun Li, Luke Pfister, and Yoram Bresler, “Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising,” in Proc. IEEE Int. Conf. Computer Vision (ICCV), 2017.

Bibtex:

@InProceedings{Wen_2017_ICCV,
  author = {Wen, Bihan and Li, Yanjun and Pfister, Luke and Bresler, Yoram},
  title = {Joint Adaptive Sparsity and Low-Rankness on the Fly: An Online Tensor Reconstruction Scheme for Video Denoising},
  booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
  month = {Oct},
  year = {2017}
}

All codes are subject to copyright and may only be used for non-commercial research. In case of use, please cite our publication.

Contact Bihan Wen ([email protected]) for any questions.

The development of this software was supported in part by the National Science Foundation (NSF) under grants CCF-13-20953 and IIS 14-47879.