The emerging of 3D video-capable embedded mobile devices is expected due to the popularization of multimedia services and the demand for novel immersive video technologies. Such devices require efficient hardware-friendly heuristics to deal with strict processing requirements and limited energy supply. To contribute to these requirements, this work presents a complete 3D-HEVC intra-frame prediction hardware design that supports a flexible coding order between texture and depth channels. The developed hardware employs hardware-friendly constraints and novel heuristics to explore inter-channel redundancies and to reduce the computational effort through the novel inter-channel directional structure detector heuristic. The designed 3D-HEVC intra-frame prediction system dissipates 384.6 mW while processing three HD 1080p views (texture + depth) at 30 frames per second in real-time. To the best of our knowledge, this is the first work to propose a complete 3D-HEVC intra-frame prediction system with support to flexible coding order. In addition, this is the only hardware design to process luminance and chrominance texture channels and depth channel.

由于多媒体服务的普及和对新型沉浸式视频技术的需求，预计将出现具有 3D 视频功能的嵌入式移动设备。此类设备需要高效的硬件友好启发式算法来处理严格的处理要求和有限的能源供应。为了满足这些要求，这项工作提出了一个完整的 3D-HEVC 帧内预测硬件设计，支持纹理和深度通道之间的灵活编码顺序。开发的硬件采用硬件友好的约束和新颖的启发式方法来探索通道间冗余并通过新颖的通道间定向结构检测器启发式方法减少计算量。设计的 3D-HEVC 帧内预测系统耗散 384。6 mW，同时以每秒 30 帧的速度实时处理三个高清 1080p 视图（纹理 + 深度）。据我们所知，这是第一个提出支持灵活编码顺序的完整 3D-HEVC 帧内预测系统的工作。此外，这是唯一处理亮度和色度纹理通道和深度通道的硬件设计。