arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.06728cs.MM
收藏

基于卷积神经网络的块上采样帧内编码

Convolutional Neural Network-Based Block Up-sampling for Intra Frame Coding

Yue Li, Dong Liu, Houqiang Li, Li Li, Feng Wu, Hong Zhang, Haitao Yang

摘要:

受卷积神经网络(CNN)图像超分辨率研究的启发,提出了一种基于CNN的块上采样帧内编码方案。块可以在通过正常帧内编码压缩之前被下采样,然后被上采样到其原始分辨率。与以往基于上下采样编码的研究不同,我们方案中的上采样方法是通过训练CNN而不是手工设计的。我们探索了一种新的上采样CNN结构,它具有特征图的反卷积,多尺度融合和残差学习,使网络既紧凑又高效。我们还分别为亮度和色度分量的上采样设计了不同的网络,其中色度上采样CNN利用亮度信息来提高其性能。此外,我们设计了一个两阶段的上采样过程,第一阶段是在逐块编码循环内,第二阶段是在整个帧上执行,以便细化块边界。我们还实证研究了如何设置下采样块的编码参数,以追求帧级率失真优化。我们提出的方案被实现到高效率视频编码(HEVC)参考软件,并进行了一系列全面的实验来评估我们的方法。实验结果表明,我们的方案实现了显着的比特节省相比,HEVC锚,特别是在低比特率,导致平均5.5%的BD率降低普通测试序列和平均9.0%的BD率降低超高清(UHD)测试序列。

英文摘要:

Inspired by the recent advances of image super-resolution using convolutional neural network (CNN), we propose a CNN-based block up-sampling scheme for intra frame coding. A block can be down-sampled before being compressed by normal intra coding, and then up-sampled to its original resolution. Different from previous studies on down/up-sampling-based coding, the up-sampling methods in our scheme have been designed by training CNN instead of hand-crafted. We explore a new CNN structure for up-sampling, which features deconvolution of feature maps, multi-scale fusion, and residue learning, making the network both compact and efficient. We also design different networks for the up-sampling of luma and chroma components, respectively, where the chroma up-sampling CNN utilizes the luma information to boost its performance. In addition, we design a two-stage up-sampling process, the first stage being within the block-by-block coding loop, and the second stage being performed on the entire frame, so as to refine block boundaries. We also empirically study how to set the coding parameters of down-sampled blocks for pursuing the frame-level rate-distortion optimization. Our proposed scheme is implemented into the High Efficiency Video Coding (HEVC) reference software, and a comprehensive set of experiments have been performed to evaluate our methods. Experimental results show that our scheme achieves significant bits saving compared with HEVC anchor especially at low bit rates, leading to on average 5.5% BD-rate reduction on common test sequences and on average 9.0% BD-rate reduction on ultra high definition (UHD) test sequences.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑