Fast Minimax Path-Based Joint Depth Interpolation
Longquan Dai; Feihu Zhang; Xing Mei; Xiaopeng Zhang
2015-05
发表期刊IEEE Signal Processing Letters
卷号22期号:5页码:623-627
摘要We propose a fast minimax path-based depth interpolation method. The algorithm computes for each target pixel varying contributions from reliable depth seeds, and weighted averaging is used to interpolate missing depths. Compared with state-of-the-art joint geodesic upsampling method which selects the K nearest seeds to interpolate missing depths with O(Kn) complexity, our method does not need to limit the number of
seeds to K  and reduces the computational complexity to O(n). In addition, the minimax path chooses a path with the smallest maximum immediate pairwise pixel difference on it, so it tends to preserve sharp depth discontinuities better. In contrast to the results of previous depth upsampling algorithms, our approach can provide accurate depths with fewer artifacts.
关键词Depth Map Minimax Path Upsampling
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/19929
专题模式识别国家重点实验室_多媒体计算与图形学
作者单位Institute of Automation Chinese Academy of Sciences, Beijing, China
推荐引用方式
GB/T 7714
Longquan Dai,Feihu Zhang,Xing Mei,et al. Fast Minimax Path-Based Joint Depth Interpolation[J]. IEEE Signal Processing Letters,2015,22(5):623-627.
APA Longquan Dai,Feihu Zhang,Xing Mei,&Xiaopeng Zhang.(2015).Fast Minimax Path-Based Joint Depth Interpolation.IEEE Signal Processing Letters,22(5),623-627.
MLA Longquan Dai,et al."Fast Minimax Path-Based Joint Depth Interpolation".IEEE Signal Processing Letters 22.5(2015):623-627.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
2015 - Fast Minimax (937KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Longquan Dai]的文章
[Feihu Zhang]的文章
[Xing Mei]的文章
百度学术
百度学术中相似的文章
[Longquan Dai]的文章
[Feihu Zhang]的文章
[Xing Mei]的文章
必应学术
必应学术中相似的文章
[Longquan Dai]的文章
[Feihu Zhang]的文章
[Xing Mei]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 2015 - Fast Minimax Path-Based Joint Depth Int.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。