| 基于非局部随机游走和运动补偿的2D转3D优化方法 |
| |
| 引用本文： | 张凝,雷建军,张翠翠,梅旭光,李乐乐.基于非局部随机游走和运动补偿的2D转3D优化方法[J].光电子．激光,2017,28(6):644-649. |
| |
| 作者姓名： | 张凝 雷建军 张翠翠 梅旭光 李乐乐 |
| |
| 作者单位： | 天津大学 电子信息工程学院,天津 300072;天津大学 电子信息工程学院,天津 300072;高德信息技术有限公司,北京 100080;天津大学 电子信息工程学院,天津 300072;天津大学 电子信息工程学院,天津 300072 |
| |
| 基金项目： | 国家自然科学基金(61271324,2,61471262,1)、国家国际合作 计划(2010DFA12780)和天津市自然科学基金(12JCYBJC10400)资助项目 (1.天津大学 电子信息工程学院,天津 300072； 2.高德信息技术有限公司,北京 100080) |
| |
| 摘 要： | D转3D技术可以从2D资源中获取深度信息,以满足3D显示对3D内容的需求。针 对2D转 3D深度估计中的深度优化问题,提出一种基于非局部随机游走(NRW)和运动补偿的 深度优化算 法。本文方法在采用NRW和移动双边滤波(SBF)获得关键帧和非关键帧深度图的基础上,为 了锐化非关 键帧深度序列对象边界,结合纹理信息利用NRW算法优化深度图,同时又考虑相邻帧间的时 域信息,采 用运动补偿的方法对非关键帧深度序列进行优化,获得高质量的深度视频序列。实验结果表 明,本文方法可以得到对象边界更加准确的深度视频估计结果。
|
| 关 键 词： | 2D转3D 深度估计 深度优化 |
| 收稿时间： | 2016/5/30 0:00:00 |
Optimization for 2D-to-3D conversion based on nonlocal random walk and motion compensation |
| |
| ZHANG Ning,LEI Jian-jun,LI Le-le,ZHANG Cui -cui and MEI Xu-guang.Optimization for 2D-to-3D conversion based on nonlocal random walk and motion compensation[J].Journal of Optoelectronics·laser,2017,28(6):644-649. |
| |
| Authors: | ZHANG Ning LEI Jian-jun LI Le-le ZHANG Cui -cui and MEI Xu-guang |
| |
| Affiliation: | School of Electronic Information Engineering,Tianjin University,Tianjin 300072,China;School of Electronic Information Engineering,Tianjin University,Tianjin 300072,China;School of Electronic Information Engineering,Tianjin University,Tianjin 300072,China;Autonavi Information Technology Co.Ltd.,Beijing 100080,China;School of Electronic Information Engineering,Tianjin University,Tianjin 300072,China |
| |
| Abstract: | Depth information can be obtained from 2-dimensional (2D) resources through 2D -to-3D conversion technology,in order to meet the demand for 3D content.In this paper,a novel approach based on nonlocal random walk (N RW) and motion compensation is proposed to solve the problem of depth map optimization in depth estimation.The depth maps of key frames and non-key frames are obtained on the basis of NRW and shif ted bilateral filtering (SBF),respectively.In order to sharpen the depth boundaries,taking texture infor mation into account,NRW is utilized to optimize the depth sequence. Considering that the temporal information of adjacent frames,motion compensation is introduced to further improve the quality of dept h maps of non-key frames.Experimental results show that,in contrast to the method directly proce ssed by SBF,our method can produce higher quality depth sequence with accurate object boundaries. |
| |
| Keywords: | 2D-to-3D conversion depth estimation depth optimization |
|
| 点击此处可从《光电子．激光》浏览原始摘要信息 |
|
点击此处可从《光电子．激光》下载全文 |
|
