Combined Internal and External Category-Specific Image Denoising

Saeed Anwar, Cong Huynh and Fatih Porikli

Abstract

In this paper, we present a category-specific image denoising algorithm that exploits patch similarity within the input image and between the input image and an external dataset. We rely on standard internal denoising for smooth regions while consulting external images in the same category as the input to denoise textured regions. The external denoising component estimates the latent patches using the statistics, i.e. means and covariance matrices, of external patches, subject to a low-rank constraint. In the final stage, we aggregate results of internal and external denoising using a weighting rule based on the patch SNR measure.

Session

Posters

Files

PDF iconPaper (PDF)
PDF iconSupplementary (PDF)

DOI

10.5244/C.31.71
https://dx.doi.org/10.5244/C.31.71

Citation

Saeed Anwar, Cong Huynh and Fatih Porikli. Combined Internal and External Category-Specific Image Denoising. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 71.1-71.12. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_71,
                title={Combined Internal and External Category-Specific Image Denoising},
                author={Saeed Anwar, Cong Huynh and Fatih Porikli},
                year={2017},
                month={September},
                pages={71.1-71.12},
                articleno={71},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.71},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.71}
            }