The evaluation of the quality of light field images is a demanding task given the peculiarities of this media. In the literature, attempts to assess quality have been done by considering specific coding approaches or visualization techniques. In this paper we intend to i) investigate whether the distortions of the light field are reflected in the distortion of the saliency map and ii) propose a metric for image quality assessment of light fields based on a convolutional neural network that exploits the measure of the distortion of the saliency map. In our tests, the annotated SMART dataset has been used. The achieved results confirm the importance of saliency for improving the performance of quality metrics.
Lamichhane, K., Battisti, F., Paudyal, P., Carli, M. (2021). Exploiting saliency in quality assessment for light field images. In 2021 Picture Coding Symposium, PCS 2021 - Proceedings (pp.1-5). 345 E 47TH ST, NEW YORK, NY 10017 USA : Institute of Electrical and Electronics Engineers Inc. [10.1109/PCS50896.2021.9477451].
Exploiting saliency in quality assessment for light field images
Lamichhane K.;Battisti F.;Paudyal P.;Carli M.
2021-01-01
Abstract
The evaluation of the quality of light field images is a demanding task given the peculiarities of this media. In the literature, attempts to assess quality have been done by considering specific coding approaches or visualization techniques. In this paper we intend to i) investigate whether the distortions of the light field are reflected in the distortion of the saliency map and ii) propose a metric for image quality assessment of light fields based on a convolutional neural network that exploits the measure of the distortion of the saliency map. In our tests, the annotated SMART dataset has been used. The achieved results confirm the importance of saliency for improving the performance of quality metrics.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
