“NoR-VDPNet++: Efficient Training and Architecture for Deep No-Reference Image Quality Metrics” by Banterle, Artusi, Moreo and Carrara

  • ©Francesco Banterle, Alessandro Artusi, Alejandro Moreo, and Fabio Carrara

  • ©Francesco Banterle, Alessandro Artusi, Alejandro Moreo, and Fabio Carrara

Conference:


Entry Number: 10

Title:

    NoR-VDPNet++: Efficient Training and Architecture for Deep No-Reference Image Quality Metrics

Presenter(s):



Abstract:


    Efficiency and efficacy are two desirable properties of the utmost importance for any evaluation metric having to do with Standard Dynamic Range (SDR) imaging or High Dynamic Range (HDR) imaging. However, these properties are hard to achieve simultaneously. On the one side, metrics like HDR-VDP2.2 are known to mimic the human visual system (HVS) very accurately, but its high computational cost prevents its widespread use in large evaluation campaigns. On the other side, computationally cheaper alternatives like PSNR or MSE fail to capture many of the crucial aspects of the HVS. In this work, we try to get the best of the two worlds: we present NoR-VDPNet++, an improved variant of a previous deep learning-based metric for distilling HDR-VDP2.2 into a convolutional neural network (CNN). In this work, we try to get the best of the two worlds: we present NoR-VDPNet++, an improved version of a deep learning-based metric for distilling HDR-VDP2.2 into a convolutional neural network (CNN).

References:


    Alessandro Artusi, Francesco Banterle, Alejandro Moreo, and Fabio Carrara. 2019. Efficient Evaluation of Image Quality via Deep-Learning Approximation of Perceptual Metrics. IEEE Transactions on Image Processing 29 (oct 2019), 1843–1855. http://vcg.isti.cnr.it/Publications/2019/ABMC19

    Tunç Ozan Aydın, Rafał Mantiuk, Karol Myszkowski, and Hans-Peter Seidel. 2008. Dynamic Range Independent Image Quality Assessment. ACM Transactions on Graphics (TOG) 27, 3, Article 69 (2008).

    Francesco Banterle, Alessandro Artusi, Alejandro Moreo, and Fabio Carrara. 2020. NoR VDPNet: A No-Reference High Dynamic Range Quality Metric Trained on HDR-VDP 2. In IEEE International Conference on Image Processing (ICIP). IEEE. http://vcg.isti.cnr.it/Publications/2020/BAMC20

    Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning. PMLR, 448–456.

    Manish Narwaria, Rafał K. Mantiuk, Mattheiu Perreira Da Silva, and Patrick Le Callet.2015. HDR-VDP-2.2: A calibrated method for objective quality prediction of high dynamic range and standard images. Journal of Electronic Imaging 24, 1 (2015).

Keyword(s):



Acknowledgements:


    This work has been supported by funding from the European Union Horizon 2020 research and innovation programme under grant agreement No 739578 for Dr. Artusi and No 820434 (ENCORE), No 813170 (EVOCATION) for Dr. Banterle respectively. The funding for the work of Dr. Artusi are also complemented by the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.


PDF:



ACM Digital Library Publication:



Type: