Local denoising based on curvature smoothing can visually outperform non-local methods on photographs with actual noise

We propose a fast, local denoising method where the Euclidean curvature of the noisy image is approximated in a regularizing manner and a clean image is reconstructed from this smoothed curvature. User preference tests show that when denoising real photographs with actual noise our method produces r...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE International Conference on Image Processing (ICIP) pp. 3111 - 3115
Main Authors Ghimpeteanu, Gabriela, Kane, David, Batard, Thomas, Levine, Stacey, Bertalmio, Marcelo
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2016
Institute of Electrical and Electronics Engineers (IEEE)
Subjects
Camera pipeline
Cameras
Image denoising
Image quality metrics
Image reconstruction
Noise measurement
Noise reduction
Perceptual metrics
Prediction algorithms
Psychophysical experiments
Visualization
Online AccessGet full text

Cover

More Information
Summary:We propose a fast, local denoising method where the Euclidean curvature of the noisy image is approximated in a regularizing manner and a clean image is reconstructed from this smoothed curvature. User preference tests show that when denoising real photographs with actual noise our method produces results with the same visual quality as the more sophisticated, nonlocal algorithms Non-local Means and BM3D, but at a fraction of their computational cost. These tests also highlight the limitations of objective image quality metrics like PSNR and SSIM, which correlate poorly with user preference.
ISBN:9781467399616
1467399612
ISSN:2381-8549
2381-8549
DOI:10.1109/ICIP.2016.7532932