当前位置:
X-MOL 学术
›
arXiv.cs.NE
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
ModeNet: Mode Selection Network For Learned Video Coding
arXiv - CS - Neural and Evolutionary Computing Pub Date : 2020-07-06 , DOI: arxiv-2007.02532 Th\'eo Ladune (IETR), Pierrick Philippe, Wassim Hamidouche (IETR), Lu Zhang (IETR), Olivier D\'eforges (IETR)
arXiv - CS - Neural and Evolutionary Computing Pub Date : 2020-07-06 , DOI: arxiv-2007.02532 Th\'eo Ladune (IETR), Pierrick Philippe, Wassim Hamidouche (IETR), Lu Zhang (IETR), Olivier D\'eforges (IETR)
In this paper, a mode selection network (ModeNet) is proposed to enhance deep
learning-based video compression. Inspired by traditional video coding, ModeNet
purpose is to enable competition among several coding modes. The proposed
ModeNet learns and conveys a pixel-wise partitioning of the frame, used to
assign each pixel to the most suited coding mode. ModeNet is trained alongside
the different coding modes to minimize a rate-distortion cost. It is a flexible
component which can be generalized to other systems to allow competition
between different coding tools. Mod-eNet interest is studied on a P-frame
coding task, where it is used to design a method for coding a frame given its
prediction. ModeNet-based systems achieve compelling performance when evaluated
under the Challenge on Learned Image Compression 2020 (CLIC20) P-frame coding
track conditions.
中文翻译:
ModeNet:用于学习视频编码的模式选择网络
在本文中,提出了一种模式选择网络(ModeNet)来增强基于深度学习的视频压缩。受传统视频编码的启发,ModeNet 的目的是实现多种编码模式之间的竞争。提议的 ModeNet 学习并传达帧的逐像素分区,用于将每个像素分配给最合适的编码模式。ModeNet 与不同的编码模式一起训练,以最小化率失真成本。它是一个灵活的组件,可以推广到其他系统以允许不同编码工具之间的竞争。Mod-eNet 兴趣是在 P 帧编码任务上研究的,它用于设计一种给定预测的帧编码方法。
更新日期:2020-08-03
中文翻译:
ModeNet:用于学习视频编码的模式选择网络
在本文中,提出了一种模式选择网络(ModeNet)来增强基于深度学习的视频压缩。受传统视频编码的启发,ModeNet 的目的是实现多种编码模式之间的竞争。提议的 ModeNet 学习并传达帧的逐像素分区,用于将每个像素分配给最合适的编码模式。ModeNet 与不同的编码模式一起训练,以最小化率失真成本。它是一个灵活的组件,可以推广到其他系统以允许不同编码工具之间的竞争。Mod-eNet 兴趣是在 P 帧编码任务上研究的,它用于设计一种给定预测的帧编码方法。