SVC中优化的上采样滤波器设计

Optimal up-sampling filter design within SVC

图像下采样后损失的信息在上采样中是无法恢复的,下采样和上采样的特定组合可以显著的影响重构图像的质量。利用这一特性,针对可分级视频编码(Scalable Video Coding,SVC)中下/上采样滤波器设计孤立存在的问题,提出一种算法,根据下采样设计与之相匹配的上采样滤波器。该算法根据已获得的下采样滤波器,推导与之对应的上采样滤波器,使两者匹配,达到提高视频质量并提升空间可分级编码性能的目的。与JSVM标准的仿真结果相比,特定组合的下/上采样滤波器在降低比特率的同时,峰值信噪比平均增加1.58 dB。

Down-sampling image results in the loss of image information that can not be recovered with up-sampling.Demonstrating that the particular combination of down-sampling and up-sampling methods used can significantly impact the reconstructed image quality.For the problem in scalable video coding that the isolate designing from down to up-sampling.The algorithm was proposed to design up-sampling filter that is matched with down-sampling filter.The algorithm based on the acquired down-sampling filter derives the corresponding up-sampling to achieve the matching purpose.It can improve not only the video quality,but also the encoding performance of the spatial scalable video coding.Compared to the simulation results of JSVM,the matching re-sampling filter designed was while reducing the bit rate,the PSNR is raised 1.58 dB on average.