Efficient evaluation of image quality via deep-learning approximation of perceptual metrics
Artusi A., Banterle F., Moreo A., Carrara F.
Convolutional Neural Networks (CNNs) Human Visual System Computer Graphics and Computer-Aided Design Human visual system Image Evaluation Objective metrics HDR imaging Objective Metrics Convolutional neural networks (CNNs) Software HDR Imaging Image evaluation JPEG-XT
Image metrics based on Human Visual System (HVS) play a remarkable role in the evaluation of complex image processing algorithms. However, mimicking the HVS is known to be complex and computationally expensive (both in terms of time and memory), and its usage is thus limited to a few applications and to small input data. All of this makes such metrics not fully attractive in real-world scenarios. To address these issues, we propose Deep Image Quality Metric ( DIQM ), a deep-learning approach to learn the global image quality feature ( mean-opinion-score ). DIQM can emulate existing visual metrics efficiently, reducing the computational costs by more than an order of magnitude with respect to existing implementations.
Source: IEEE transactions on image processing (Online) 29 (2019): 1843–1855. doi:10.1109/TIP.2019.2944079
Publisher: Institute of Electrical and Electronics Engineers,, New York, NY , Stati Uniti d'America
Metrics
Back to previous page
@article{oai:it.cnr:prodotti:411498,
title = {Efficient evaluation of image quality via deep-learning approximation of perceptual metrics},
author = {Artusi A. and Banterle F. and Moreo A. and Carrara F.},
publisher = {Institute of Electrical and Electronics Engineers,, New York, NY , Stati Uniti d'America},
doi = {10.1109/tip.2019.2944079},
journal = {IEEE transactions on image processing (Online)},
volume = {29},
pages = {1843–1855},
year = {2019}
}
0000-0002-6374-6657ISTI Repository
DOIAlso available from
ZENODO
IEEE Transactions on Image Processing
ieeexplore.ieee.org
