Learning-Based JND-Directed HDR Video Preprocessing for Perceptually Lossless Compression With HEVC
Learning-Based JND-Directed HDR Video Preprocessing for Perceptually Lossless Compression With HEVC
复制标题
DOI：
10.1109/access.2020.3046194
复制
发表时间：
2020-01-01
期刊：
影响因子：
3.9
通讯作者：
Kim, Munchurl
中科院分区：
文献类型：
--
作者：
Ki, Sehwan;Do, Jeonghyeok;Kim, Munchurl
视频的最终消费者主要是人类。因此，如果能够充分利用人类视觉系统（HVS）的感知特性来压缩视频，则可以在尽可能少地降低主观视觉质量下降的情况下显著降低压缩视频的比特率。在此基础上，我们新提出了一种基于学习的JND（Just Noticeable Distortion）指导的感知视频压缩预处理方案，特别是针对10位高动态范围（HDR）视频，称为HDR-JNDNet。我们的HDR-JNDNet有效地抑制了10位HDR视频信号的感知冗余，因此可以显着提高HEVC main 10 profile编码器的压缩效率。据我们所知，我们的工作是第一种训练基于CNN的模型的方法，以直接生成10位HDR视频的JND定向抑制帧，其中原始HDR视频输入的解码帧之间的感知质量差异可以忽略不计，无论是否经过HDR-JNDNet的预处理。通过大量的实验，当HDR-JNDNet在压缩前应用于HDR视频输入的预处理时，它可以显着节省4K-UHD/HDR测试视频所需的最大（平均）40.66%（18.37%）的比特率，并且在不增加计算复杂度的情况下几乎没有主观视频质量下降。
The final consumer of videos is mostly human. Therefore, if videos can be compressed by fully utilizing the perception characteristics of human visual systems (HVS), the bitrates of the compressed videos can be significantly reduced with subjective visual quality degradation as little as possible. Based on this, we newly propose a learning-based Just Noticeable Distortion (JND)-directed preprocessing scheme for perceptual video compression, especially for 10-bit High Dynamic Range (HDR) videos, which is called the HDR-JNDNet. Our HDR-JNDNet effectively suppresses the perceptual redundancy of 10-bit HDR video signals so that the compression efficiency can be significantly enhanced for the HEVC main10 profile encoder. To our best knowledge, our work is the first approach to training a CNN-based model to directly generate the JND-directed suppressed frames of 10-bit HDR video with the negligible perceptual quality difference between the decoded frames for the original HDR video input with and without the preprocessing by our HDR-JNDNet. Via intensive experiments, when the HDR-JNDNet is applied as preprocessing for the HDR video input before compression, it allows to remarkably save the required bitrates up to the maximum (average) 40.66% (18.37%) for 4K-UHD/HDR test videos, with little subjective video quality degradation without increasing the computational complexity.