Journal article Open Access

Efficient Evaluation of Image Quality via Deep-Learning Approximation of Perceptual Metrics

Artusi Alessandro; Banterle Francesco; Carrara Fabio; Moreo Alejandro

mage 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

This work has received funding from the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No 739578 and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.
Files (21.6 MB)
Name Size
TIP2944079.pdf
md5:5876f0ae8d402aae845b9c8db6c32989
21.6 MB Download
60
45
views
downloads
Views 60
Downloads 45
Data volume 973.8 MB
Unique views 54
Unique downloads 43

Share

Cite as