基于SSIM和SAD的AVS帧内预测模式改进算法

Improvements for AVS Intra Mode Selection Based on SSIM and SAD

在AVS帧内预测模式的选择过程中,以绝对误差和(SAD)作为失真度量,通过相应的i_sad代价函数进行选择,但是这种方法被证明不能很好地符合人眼视觉(HVS)。由于结构相似度(SSIM)算法相对简单,准确性好,优于传统的PSNR等方法,因此提出了将SSIM和SAD作为帧内预测模式选择的标准。实验表明,将SSIM和SAD用于AVS帧内预测模式选择,获得了比原AVS更好的重建图像质量和更高的编码压缩率。

In the mode selection process of AVS intra prediction, Sum of absolute differences （ SAD ） is used as distortion measurement and choose the current block prediction mode from the i_sad cost, but this measure is proved not to be fit in with human visual （ HVS ） well. Referring to AVS, the structural similarity （ SSIM ）is used in this paper, Its algorithm is relatively simple, and it has good accuracy, so it is better than traditional methods such as PSNR. The SSIM and SAD are put foward as an intra prediction mode selection standard. Results show that the proposed algorithm can achieve better image quality and the better coding efficiency.