arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.04557cs.CVeess.IV
收藏

场景至关重要:基于模型的深度视频压缩

Scene Matters: Model-based Deep Video Compression

University of Chinese Academy of Sciences(中国科学院大学)

Lv Tang, Xinfeng Zhang, Gai Zhang, Xiaoqi Ma

AI总结:

本文提出一种基于场景的模型驱动视频压缩框架,利用隐式神经表示直接建模视频强度变化,通过空间位置嵌入、频域监督、场景流约束和时间对比损失提升效率,相比H.266实现高达20%码率降低且解码更高效。

摘要:

视频压缩一直是一个热门的研究领域,其中已经提出了许多传统和深度视频压缩方法。这些方法通常依赖于信号预测理论,通过设计高效的帧内和帧间预测策略并逐帧压缩视频帧来提升压缩性能。在本文中,我们提出了一种新颖的基于模型的视频压缩(MVC)框架,该框架将场景视为视频序列的基本单元。我们提出的MVC直接对一个场景中整个视频序列的强度变化进行建模,寻求非冗余表示,而不是通过时空预测来减少冗余。为了实现这一点,我们采用隐式神经表示作为我们的基本建模架构。为了提高视频建模的效率,我们首先在空间上下文增强中提出了上下文相关的空间位置嵌入和频域监督。对于时间相关性捕获,我们设计了场景流约束机制和时间对比损失。大量的实验结果表明,与最新的视频编码标准H.266相比,我们的方法实现了高达20%的码率降低,并且在解码方面比现有的视频编码策略更高效。

英文摘要:

Video compression has always been a popular research area, where many traditional and deep video compression methods have been proposed. These methods typically rely on signal prediction theory to enhance compression performance by designing high efficient intra and inter prediction strategies and compressing video frames one by one. In this paper, we propose a novel model-based video compression (MVC) framework that regards scenes as the fundamental units for video sequences. Our proposed MVC directly models the intensity variation of the entire video sequence in one scene, seeking non-redundant representations instead of reducing redundancy through spatio-temporal predictions. To achieve this, we employ implicit neural representation as our basic modeling architecture. To improve the efficiency of video modeling, we first propose context-related spatial positional embedding and frequency domain supervision in spatial context enhancement. For temporal correlation capturing, we design the scene flow constrain mechanism and temporal contrastive loss. Extensive experimental results demonstrate that our method achieves up to a 20\% bitrate reduction compared to the latest video coding standard H.266 and is more efficient in decoding than existing video coding strategies.

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。

↑