Lightweight implementation of No-Reference (NR) perceptual quality assessment of H.264/AVC compression
作者：
Highlights：
• We propose NR metric implementation to objectively assess H.264/AVC quality.
• Proposed model takes into account typical artefacts introduced by video codecs.
• Accuracy of proposed quality metric is validated over subjective data and SSIM.
• Our metric has higher Pearson׳s correlation with subjective scores than SSIM.
• Our implementation is lightweight to perform real-time quality calculations.
摘要
Highlights•We propose NR metric implementation to objectively assess H.264/AVC quality.•Proposed model takes into account typical artefacts introduced by video codecs.•Accuracy of proposed quality metric is validated over subjective data and SSIM.•Our metric has higher Pearson׳s correlation with subjective scores than SSIM.•Our implementation is lightweight to perform real-time quality calculations.
论文关键词：Quality of Experience (QoE),Video Artefacts,Quality Metrics,H.264,Implementation
论文评审过程：Received 30 September 2014, Revised 4 April 2015, Accepted 13 May 2015, Available online 19 May 2015, Version of Record 18 November 2015.
论文官网地址：https://doi.org/10.1016/j.image.2015.05.003
