Banterle F., Artusi A., Moreo A., Carrara F.
Deep learning Image quality assessment Hdr-Vdp NoR-VDPNet No reference
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 deeplearning approach that learns to predict the global image quality feature (i.e., the mean-opinion-score index Q) that HDRVDP 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.
Source: IEEE International Conference on Image Processing (ICIP 2020), pp. 126–130, Abu Dhabi, United Arab Emirates, United Arab Emirates, 25/10/2020-28/10/2020
Publisher: IEEE, New York, USA
@inproceedings{oai:it.cnr:prodotti:438799, title = {Nor-Vdpnet: a no-reference high dynamic range quality metric trained on Hdr-Vdp 2}, author = {Banterle F. and Artusi A. and Moreo A. and Carrara F.}, publisher = {IEEE, New York, USA}, doi = {10.1109/icip40778.2020.9191202}, booktitle = {IEEE International Conference on Image Processing (ICIP 2020), pp. 126–130, Abu Dhabi, United Arab Emirates, United Arab Emirates, 25/10/2020-28/10/2020}, year = {2020} }
Postprint version
Preprint version
10.1109/icip40778.2020.9191202