In 3D extension of HEVC (High Efficiency Video coding), namely, 3D-HEVC, segment-wise dc coding (Sdc) was adopted to more efficiently represent the depth residual for Intra coded depth blocks. Instead of coding pixel-...
详细信息
ISBN:
(纸本)9781479957521
In 3D extension of HEVC (High Efficiency Video coding), namely, 3D-HEVC, segment-wise dc coding (Sdc) was adopted to more efficiently represent the depth residual for Intra coded depth blocks. Instead of coding pixel-wise residual as in HEVC, Sdc codes one dc residual value for each segment of a Prediction Unit (PU) and skips transform and quantization. Sdc was originally proposed for only a couple of modes, including the dc mode, Planar mode and depth modeling mode (DMM), which has an arbitrary straight line separation of a PU. This paper proposes a generic Sdc method that applies to the conventional angular Intra modes. For each depth prediction unit coded with Intra prediction mode, encoder can adaptively choose to code pixel-wise residual or segment-wise residual to achieve better compression efficiency. Experimental results show that proposed method can reduce the total bit rate by about 1% even though the depth views altogether consumes relatively low percentage of the total bit rate.
暂无评论