HackerPapers

arXiv:2001.01802cs.CV

Implementation of the VBM3D Video Denoising Method and Some Variants

Thibaud Ehret, Pablo Arias

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

Abstract

VBM3D is an extension to video of the well known image denoising algorithm BM3D, which takes advantage of the sparse representation of stacks of similar patches in a transform domain. The extension is rather straightforward: the similar 2D patches are taken from a spatio-temporal neighborhood which includes neighboring frames. In spite of its simplicity, the algorithm offers a good trade-off between denoising performance and computational complexity. In this work we revisit this method, providing an open-source C++ implementation reproducing the results. A detailed description is given and the choice of parameters is thoroughly discussed. Furthermore, we discuss several extensions of the original algorithm: (1) a multi-scale implementation, (2) the use of 3D patches, (3) the use of optical flow to guide the patch search. These extensions allow to obtain results which are competitive with even the most recent state of the art.

arXiv comments
18 pages, 7 figures, 5 tables
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from Jul 2025 to Jul 2025.

Comments linking this paper, per year.

Discussed in comments1 thread

    • Don't want to sound too snarky, but aren't you just saying that good denoisers must be temporal in addition to spatial? Something like an improved V-BM3D (cf https://arxiv.org/abs/2001.01802) and even traditional V-BM3D works fine even on non-Gaussian noise. Together with…

      BoingBoomTschakView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.