NoR-VDPNet++: Real-Time No-Reference Image Quality Metrics
Efficiency and efficacy are desirable properties for any evaluation metric having to do with Standard Dynamic Range (SDR) imaging or with High Dynamic Range (HDR) imaging. However, it is a daunting task to satisfy both properties simultaneously. On the one side, existing evaluation metrics like HDR-...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10089442/ |
| _version_ | 1797846461370597376 |
|---|---|
| author | Francesco Banterle Alessandro Artusi Alejandro Moreo Fabio Carrara Paolo Cignoni |
| author_facet | Francesco Banterle Alessandro Artusi Alejandro Moreo Fabio Carrara Paolo Cignoni |
| author_sort | Francesco Banterle |
| collection | DOAJ |
| description | Efficiency and efficacy are desirable properties for any evaluation metric having to do with Standard Dynamic Range (SDR) imaging or with High Dynamic Range (HDR) imaging. However, it is a daunting task to satisfy both properties simultaneously. On the one side, existing evaluation metrics like HDR-VDP 2.2 can accurately mimic the Human Visual System (HVS), but this typically comes at a very high computational cost. On the other side, computationally cheaper alternatives (e.g., PSNR, MSE, etc.) fail to capture many crucial aspects of the HVS. In this work, we present NoR-VDPNet++, a deep learning architecture for converting full-reference accurate metrics into no-reference metrics thus reducing the computational burden. We show NoR-VDPNet++ can be successfully employed in different application scenarios. |
| first_indexed | 2024-04-09T17:56:26Z |
| format | Article |
| id | doaj.art-02c41e14b9d14ab0a841958ad94ac655 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-09T17:56:26Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-02c41e14b9d14ab0a841958ad94ac6552023-04-14T23:00:16ZengIEEEIEEE Access2169-35362023-01-0111345443455310.1109/ACCESS.2023.326349610089442NoR-VDPNet++: Real-Time No-Reference Image Quality MetricsFrancesco Banterle0https://orcid.org/0000-0002-6374-6657Alessandro Artusi1https://orcid.org/0000-0002-4502-663XAlejandro Moreo2https://orcid.org/0000-0002-0377-1025Fabio Carrara3https://orcid.org/0000-0001-5014-5089Paolo Cignoni4https://orcid.org/0000-0002-2686-8567ISTI-CNR, Pisa, ItalyCYENS CoE, Nicosia, DeepCamera, CyprusISTI-CNR, Pisa, ItalyISTI-CNR, Pisa, ItalyISTI-CNR, Pisa, ItalyEfficiency and efficacy are desirable properties for any evaluation metric having to do with Standard Dynamic Range (SDR) imaging or with High Dynamic Range (HDR) imaging. However, it is a daunting task to satisfy both properties simultaneously. On the one side, existing evaluation metrics like HDR-VDP 2.2 can accurately mimic the Human Visual System (HVS), but this typically comes at a very high computational cost. On the other side, computationally cheaper alternatives (e.g., PSNR, MSE, etc.) fail to capture many crucial aspects of the HVS. In this work, we present NoR-VDPNet++, a deep learning architecture for converting full-reference accurate metrics into no-reference metrics thus reducing the computational burden. We show NoR-VDPNet++ can be successfully employed in different application scenarios.https://ieeexplore.ieee.org/document/10089442/Deep learningHDR imagingobjective metricsno-reference |
| spellingShingle | Francesco Banterle Alessandro Artusi Alejandro Moreo Fabio Carrara Paolo Cignoni NoR-VDPNet++: Real-Time No-Reference Image Quality Metrics IEEE Access Deep learning HDR imaging objective metrics no-reference |
| title | NoR-VDPNet++: Real-Time No-Reference Image Quality Metrics |
| title_full | NoR-VDPNet++: Real-Time No-Reference Image Quality Metrics |
| title_fullStr | NoR-VDPNet++: Real-Time No-Reference Image Quality Metrics |
| title_full_unstemmed | NoR-VDPNet++: Real-Time No-Reference Image Quality Metrics |
| title_short | NoR-VDPNet++: Real-Time No-Reference Image Quality Metrics |
| title_sort | nor vdpnet x002b x002b real time no reference image quality metrics |
| topic | Deep learning HDR imaging objective metrics no-reference |
| url | https://ieeexplore.ieee.org/document/10089442/ |
| work_keys_str_mv | AT francescobanterle norvdpnetx002bx002brealtimenoreferenceimagequalitymetrics AT alessandroartusi norvdpnetx002bx002brealtimenoreferenceimagequalitymetrics AT alejandromoreo norvdpnetx002bx002brealtimenoreferenceimagequalitymetrics AT fabiocarrara norvdpnetx002bx002brealtimenoreferenceimagequalitymetrics AT paolocignoni norvdpnetx002bx002brealtimenoreferenceimagequalitymetrics |