HEVC Inter Coding using Deep Recurrent Neural Networks and Artificial Reference Pictures
HEVC Inter Coding using Deep Recurrent Neural Networks and Artificial Reference Pictures
复制标题
DOI：
10.1109/pcs48520.2019.8954497
复制
发表时间：
2018-12
期刊：
影响因子：
--
通讯作者：
Felix Haub;Thorsten Laude;J. Ostermann
中科院分区：
文献类型：
--
作者：
Felix Haub;Thorsten Laude;J. Ostermann
现代视频编解码器中的运动补偿预测的效率高度依赖于可用的参考图片。遮挡和非线性运动对运动补偿提出了挑战，并且通常导致预测误差的高比特率。我们提出使用深度递归神经网络生成人工参考图片。在概念上，当前编码图片的时间实例处的参考图片是从先前重构的常规参考图片生成的。基于这些人工参考图片，我们提出了一个完整的基于HEVC的编码流水线。通过使用用于运动补偿预测的人工参考图片，实现了相对于HEVC的1.5%的平均BD速率增益。
The efficiency of motion compensated prediction in modern video codecs highly depends on the available reference pictures. Occlusions and non-linear motion pose challenges for the motion compensation and often result in high bit rates for the prediction error. We propose the generation of artificial reference pictures using deep recurrent neural networks. Conceptually, a reference picture at the time instance of the currently coded picture is generated from previously reconstructed conventional reference pictures. Based on these artificial reference pictures, we propose a complete coding pipeline based on HEVC. By using the artificial reference pictures for motion compensated prediction, average BD-rate gains of 1.5% over HEVC are achieved.