Synthesizing Camera Noise Using Generative Adversarial Networks

We present a technique for synthesizing realistic noise for digital photographs. It can adjust the noise level of an input photograph, either increasing or decreasing it, to match a target ISO level. Our solution learns the mappings among different ISO levels from unpaired data using generative adve...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on visualization and computer graphics 2021-03, Vol.27 (3), p.2123-2135
Main Authors: Henz, Bernardo, Gastal, Eduardo S. L., Oliveira, Manuel M.
Format: Article
Language:English
Subjects:
AWGN
Cameras
deep learning
GANs
Generative adversarial networks
ISO
ISO Standards
Kolmogorov-Smirnov test
Noise
Noise level
Noise levels
Noise model
Noise reduction
Synthesis
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a technique for synthesizing realistic noise for digital photographs. It can adjust the noise level of an input photograph, either increasing or decreasing it, to match a target ISO level. Our solution learns the mappings among different ISO levels from unpaired data using generative adversarial networks. We demonstrate its effectiveness both quantitatively, using Kullback-Leibler divergence and Kolmogorov-Smirnov test, and qualitatively through a large number of examples. We also demonstrate its practical applicability by using its results to significantly improve the performance of a state-of-the-art trainable denoising method. Our technique should benefit several computer-vision applications that seek robustness to noisy scenarios.
ISSN:1077-2626
1941-0506
DOI:10.1109/TVCG.2020.3012120