ViDeNN: Deep Blind Video Denoising

CVPRW 2019 pp. 1843-1852

doi:10.1109/CVPRW.2019.00235 /cvprw/2019/claus2019cvprw-videnn/

Abstract

We propose ViDeNN: a CNN for Video Denoising without prior knowledge on the noise distribution (blind denoising). The CNN architecture uses a combination of spatial and temporal filtering, learning to spatially denoise the frames first and at the same time how to combine their temporal information, handling objects motion, brightness changes, low-light conditions and temporal inconsistencies. We demonstrate the importance of the data used for CNNs training, creating for this purpose a specific dataset for low-light conditions. We test ViDeNN on common benchmarks and on self-collected data, achieving good results comparable with the state-of-the-art.

PDF CVPRW Semantic Scholar

Cite

Text

Claus and van Gemert. "ViDeNN: Deep Blind Video Denoising." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00235

Markdown

[Claus and van Gemert. "ViDeNN: Deep Blind Video Denoising." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/claus2019cvprw-videnn/) doi:10.1109/CVPRW.2019.00235

BibTeX

@inproceedings{claus2019cvprw-videnn,
  title     = {{ViDeNN: Deep Blind Video Denoising}},
  author    = {Claus, Michele and van Gemert, Jan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2019},
  pages     = {1843-1852},
  doi       = {10.1109/CVPRW.2019.00235},
  url       = {https://mlanthology.org/cvprw/2019/claus2019cvprw-videnn/}
}