NoR-VDPNet: A No-Reference High-Dynamic-Range Quality Metric Trained on HDR-VDP 2

Authors : F. Banterle, A. Artusi, A. Moreo and F. Carrara

October, 2020 IEEE International conference on image processing (ICIP), DOI:……

“(c) 20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.”

F. Banterle, A. Artusi, A. Moreo and F. Carrara

NoR-VDPNet: A No-Reference High-Dynamic-Range Quality Metric Trained on HDR-VDP 2

PDF Code DOI

F. Banterle, A. Artusi, A. Moreo and F. Carrara, “Nor-Vdpnet: A No-Reference High Dynamic Range Quality Metric Trained On Hdr-Vdp 2,” 2020 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, 2020, pp. 126-130, doi: 10.1109/ICIP40778.2020.9191202.

@INPROCEEDINGS{9191202,
author={F. {Banterle} and A. {Artusi} and A. {Moreo} and F. {Carrara}},
booktitle={2020 IEEE International Conference on Image Processing (ICIP)},
title={Nor-Vdpnet: A No-Reference High Dynamic Range Quality Metric Trained On Hdr-Vdp 2},
year={2020},
volume={},
number={},
pages={126-130},
doi={10.1109/ICIP40778.2020.9191202}}

HDR-VDP 2 has convincingly shown to be a reliable metric for image quality assessment, and it is currently playing a remarkable role in the evaluation of complex image processing algorithms. However, HDR-VDP 2 is known to be computationally expensive (both in terms of time and memory) and is constrained to the availability of a ground-truth image (the so-called reference) against to which the quality of a processed imaged is quantified. These aspects impose severe limitations on the applicability of HDR-VDP 2 to realworld scenarios involving large quantities of data or requiring real-time responses. To address these issues, we propose Deep No-Reference Quality Metric (NoR-VDPNet), a deep-learning approach that learns to predict the global image quality feature (i.e., the mean-opinion-score index Q) that HDR-VDP 2 computes. NoR-VDPNet is no-reference (i.e., it operates without a ground truth reference) and its computational cost is substantially lower when compared to HDR-VDP 2 (by more than an order of magnitude). We demonstrate the performance of NoR-VDPNet in a variety of scenarios, including the optimization of parameters of a denoiser and JPEG-XT.