版权说明 操作指南
首页 > 成果 > 详情

Tunable early CU size decision for depth map intra coding in 3D-HEVC using unsupervised learning

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Li, Yue;Yang, Gaobo;Qu, Aiping;Zhu, Yapei
通讯作者:
Yang, GB
作者机构:
[Qu, Aiping; Li, Yue] Univ South China, Comp Sch, Hengyang 421001, Peoples R China.
[Yang, Gaobo; Yang, GB] Hunan Univ, Sch Informat Sci & Engn, Changsha 410082, Peoples R China.
[Zhu, Yapei] Hengyang Normal Univ, Fac Phys & Elect Informat Sci, Hengyang 421002, Peoples R China.
通讯机构:
[Yang, GB ] H
Hunan Univ, Sch Informat Sci & Engn, Changsha 410082, Peoples R China.
语种:
英文
关键词:
3D-HEVC;Unsupervised learning;Depth map;CU size decision;RD cost
期刊:
Digital Signal Processing
ISSN:
1051-2004
年:
2022
卷:
123
页码:
103448
基金类别:
National Natural Sci-ence Foundation of ChinaNational Natural Science Foundation of China (NSFC) [62001209, 61972143]; Natural Science Foundation of Hunan Province, ChinaNatural Science Foundation of Hunan Province [2020JJ5496]
机构署名:
本校为其他机构
院系归属:
物理与电子工程学院
摘要:
To further improve coding gain for depth map in 3D extension of High Efficiency Video Coding (3D-HEVC), many new coding techniques are introduced, which drastically increase the coding complexity. In this work, an early intra coding unit (CU) size decision scheme is proposed for 3D-HEVC intra depth map coding based on unsupervised learning approach. First, we treat the early CU size decision as a clustering problem. Then, three clustering models are developed for those CUs with the sizes of 64×64, 32×32 and 16×16 to early determine whether t...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com