SGDNet : an end-to-end saliency-guided deep neural network for no-reference image quality assessment

• Main Authors: Yang, Sheng, Jiang, Qiuping, Lin, Weisi, Wang, Yongtao
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2020
• Subjects: Engineering::Computer science and engineering; Image Quality Assessment; No-reference
• Online Access: https://hdl.handle.net/10356/144191; https://doi.org/10.21979/N9/H38R0Z
• Institution: Nanyang Technological University

We propose an end-to-end saliency-guided deep neural network (SGDNet) for no-reference image quality assessment (NR-IQA). Our SGDNet is built on an end-to-end multi-task learning framework in which two sub-tasks including visual saliency prediction and image quality prediction are jointly optimized...