Visual Perception Based Intra Coding Algorithm for H.266/VVC

The latest international video coding standard, H.266/Versatile Video Coding (VVC), supports high-definition videos, with resolutions from 4 K to 8 or even larger. It offers a higher compression ratio than its predecessor, H.265/High Efficiency (HEVC). In addition the quadtree partition structure of H.265/HEVC, nested multi-type tree (MTT) H.266/VVC provides more diverse splits through binary and ternary trees. also includes many new tools, which tremendously increases encoding complexity. This paper proposes fast intra algorithm for based on visual perception analysis. applies factor average background luminance just-noticeable-distortion identify visually distinguishable (VD) pixels within unit (CU). We propose calculating variances numbers VD in various MTT CU. Intra sub-partitions matrix weighted prediction are turned off conditionally variance four thresholding criterion. horizontal/vertical splitting decisions trees proposed by utilizing random forest classifiers machine learning techniques, use information quantization parameter. Experimental results show that achieves around 47.26% time reduction Bjøntegaard Delta Bitrate (BDBR) 1.535% under All configuration. Overall, this can significantly speed up outperform previous studies.