arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2111.03386eess.IVcs.CV
收藏

多功能学习视频压缩

Versatile Learned Video Compression

University of Science and Technology of China(中国科学技术大学);Microsoft Research Asia(微软亚洲研究院)

Runsen Feng, Zongyu Guo, Zhizheng Zhang, Zhibo Chen

摘要:

学习的视频压缩方法已经证明了很大的希望,赶上传统的视频编解码器在其率失真(R-D)的性能。然而,现有的学习视频压缩方案受到预测模式和固定网络框架的绑定的限制。它们不能支持各种帧间预测模式,因此不适用于各种场景。在本文中,为了打破这一限制,我们提出了一个通用的学习视频压缩(VLVC)框架,使用一个模型来支持所有可能的预测模式。具体地,为了实现通用压缩,我们首先构建运动补偿模块,其应用多个3D运动矢量场(即,体素流)用于时空空间中的加权三线性扭曲。体素流传达时间参考位置的信息,这有助于将帧间预测模式与框架设计解耦。其次,在多参考帧预测的情况下,我们应用一个流预测模块来预测准确的运动轨迹与统一的多项式函数。我们表明,流量预测模块可以大大降低体素流的传输成本。实验结果表明,我们提出的VLVC不仅支持各种设置下的通用压缩,而且是第一个端到端学习视频压缩方法,在MS-SSIM方面优于最新的VVC/H.266标准参考软件。

英文摘要:

Learned video compression methods have demonstrated great promise in catching up with traditional video codecs in their rate-distortion (R-D) performance. However, existing learned video compression schemes are limited by the binding of the prediction mode and the fixed network framework. They are unable to support various inter prediction modes and thus inapplicable for various scenarios. In this paper, to break this limitation, we propose a versatile learned video compression (VLVC) framework that uses one model to support all possible prediction modes. Specifically, to realize versatile compression, we first build a motion compensation module that applies multiple 3D motion vector fields (i.e., voxel flows) for weighted trilinear warping in spatial-temporal space. The voxel flows convey the information of temporal reference position that helps to decouple inter prediction modes away from framework designing. Secondly, in case of multiple-reference-frame prediction, we apply a flow prediction module to predict accurate motion trajectories with unified polynomial functions. We show that the flow prediction module can largely reduce the transmission cost of voxel flows. Experimental results demonstrate that our proposed VLVC not only supports versatile compression in various settings, but also is the first end-to-end learned video compression method that outperforms the latest VVC/H.266 standard reference software in terms of MS-SSIM.

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。

↑