Full-Reference Stereoscopic Video Quality Assessment Using a Motion Sensitive HVS Model

Stereoscopic video quality assessment has become a major research topic in recent years. Existing stereoscopic metrics are predominantly based on image extended to the time domain via for example temporal pooling. These approaches do not explicitly consider motion sensitivity of Human Visual System (HVS). To address this limitation, paper introduces novel HVS model inspired by physiological findings characterising sensitive response complex cells primary visual cortex (V1 area). The proposed generalises previous models, which characterised behaviour simple and but ignored sensitivity, estimating optical flow measure scene velocity at different scales orientations. local characteristics (direction amplitude) used modulate output cells. is applied develop new type full-reference uniquely combine non-motion energy terms mimic HVS. A tailored two-stage multi-variate stepwise regression algorithm introduced determine optimal contribution each term. two evaluated three datasets. Results indicate that they achieve average correlations with subjective scores 0.9257 (PLCC), 0.9338 0.9120 (SRCC), 0.8622 0.8306 (KRCC), outperform including other HVS-based metrics.