arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.08147eess.IVcs.CVcs.LG
收藏

感知启发压缩视频的超分辨率

Perceptually-inspired super-resolution of compressed videos

University of Bristol(布里斯托大学)

Di Ma, Mariana Afonso, Fan Zhang, David R. Bull

摘要:

空间分辨率自适应是一种在视频压缩中经常采用的提高编码效率的技术。这种方法对输入视频的较低分辨率版本进行编码,并在解码期间重建原始分辨率。最近的工作采用了基于卷积神经网络(CNN)的高级超分辨率方法,而不是使用传统的上采样滤波器,以进一步提高重建质量。这些方法通常被训练为最小化基于像素的损失,例如均方误差(MSE),尽管这种类型的损失度量与主观意见没有很好的相关性。在本文中,感知启发的超分辨率方法(M-SRGAN)提出了使用修改后的CNN模型,已使用生成对抗网络(GAN)与感知损失函数的压缩内容上训练的压缩视频的空间上采样。所提出的方法与HEVC HM 16.20集成,并且已经使用随机访问配置在JVET公共测试条件(UHD测试序列)上进行了评估。结果显示,与原始HM 16.20相比,感知质量有了明显的改善,基于感知质量度量VMAF的平均比特率节省了35.6%(Bjøntegaard Delta测量)。

英文摘要:

Spatial resolution adaptation is a technique which has often been employed in video compression to enhance coding efficiency. This approach encodes a lower resolution version of the input video and reconstructs the original resolution during decoding. Instead of using conventional up-sampling filters, recent work has employed advanced super-resolution methods based on convolutional neural networks (CNNs) to further improve reconstruction quality. These approaches are usually trained to minimise pixel-based losses such as Mean-Squared Error (MSE), despite the fact that this type of loss metric does not correlate well with subjective opinions. In this paper, a perceptually-inspired super-resolution approach (M-SRGAN) is proposed for spatial up-sampling of compressed video using a modified CNN model, which has been trained using a generative adversarial network (GAN) on compressed content with perceptual loss functions. The proposed method was integrated with HEVC HM 16.20, and has been evaluated on the JVET Common Test Conditions (UHD test sequences) using the Random Access configuration. The results show evident perceptual quality improvement over the original HM 16.20, with an average bitrate saving of 35.6% (Bjøntegaard Delta measurement) based on a perceptual quality metric, VMAF.

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。

↑