可提高超压缩效率的上下文自适应熵编码器（英文）

Structure and context adaptive entropy coders for ultra-compression efficiency

对丰富视觉内容和交互性的研究,极大提高了下一代视频技术所能传输的原始数据量。2016年即将商业发布120fps全超高清电视(FUHDTV),其每秒内所能传输的原始像素,是澳大利亚免费电视目前所用最佳传输格式HDTVi的128倍。人们对于120-多视点广播HDTVi格式的数据量有着类似增长预期。最新的高效视频编码(HEVC)标准相当灵活,足以为FUHDTV和120-多视点广播提供编码数据流支持,但通过传统广播网络传输这种数据流所需的超压缩效率,与当前最高水平的上下文自适应熵编码器还不匹配。一种能采用结构相似性的一般编码范式将被给出,来大幅提升现有上下文自适应编码器的压缩效率。

Our appetite for rich visual contents and interactivity has led to a huge jump in raw data volume of future generation video technologies.Contents for the Full Ultra High Definition TV（FUHDTV）at 120 fps,to be commercially released overseas late this year,has to pack 128 times more raw pixels per second compared to HDTVi,the current best transmission format of Australian free-to-air TVs.A similar growth in data volume is expected for a multiview broadcasting in HDTVi format with 120 viewpoints.While the latest High Efficiency Video Coding（HEVC）standard is flexible enough to support encoding data streams for both FUHDTV and multiview broadcasting with as many as 120 viewpoints,the ultra-compression efficiency needed to transmit such streams via traditional broadcasting networks cannot be met with the current state-of-the-art context-adaptive entropy coders.A generalized coding paradigm capable of exploiting structural-similarity will be presented here to significantly improve compression efficiency of the existing context-adaptive coders.