Hybrid Tree Guided PatchMatch and Quantizing Acceleration for Multiple Views Disparity Estimation
Jiguang,Zhang; Shibiao,Xu; Xiaopeng,Zhang
刊名中国体视学与图像分析
2021-03
卷号26期号:1页码:47-61
关键词stereo matching multiple views disparity estimation hybrid tree patch match
英文摘要
Existing stereo matching methods cannot guarantee both the computational accuracy and efficiency for the disparity estimation of large-scale or multi-view images. Hybrid tree method can obtain a disparity estimation fast with relatively low accuracywhile PatchMatch can give high-precision disparity value with relatively high computational cost. In this workwe propose the Hybrid Tree Guided PatchMatch which can calculate the disparity fast and accurate. Firstlyan initial disparity map is estimated by employing hybrid tree cost aggregationwhich is used to constrain the label searching range of the PatchMatch. Furthermorea reliable normal searching range for each current normal vector defined on the initial disparity map is calculated to refine the PatchMatch. Finallyan effective quantizing acceleration strategy is designed to decrease the matching computational cost of continuous disparity. Experimental results demonstrate that the disparity estimation based on our algorithm is better in binocular image benchmarks such as Middlebury and KITTI. We also provide the disparity estimation results for multi-view stereo in real scenes.
语种英语
内容类型期刊论文
源URL[http://ir.ia.ac.cn/handle/173211/47460]  
专题模式识别国家重点实验室_三维可视计算
通讯作者Shibiao,Xu
作者单位Institute of Automation, Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Jiguang,Zhang,Shibiao,Xu,Xiaopeng,Zhang. Hybrid Tree Guided PatchMatch and Quantizing Acceleration for Multiple Views Disparity Estimation[J]. 中国体视学与图像分析,2021,26(1):47-61.
APA Jiguang,Zhang,Shibiao,Xu,&Xiaopeng,Zhang.(2021).Hybrid Tree Guided PatchMatch and Quantizing Acceleration for Multiple Views Disparity Estimation.中国体视学与图像分析,26(1),47-61.
MLA Jiguang,Zhang,et al."Hybrid Tree Guided PatchMatch and Quantizing Acceleration for Multiple Views Disparity Estimation".中国体视学与图像分析 26.1(2021):47-61.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
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。


©版权所有 ©2017 CSpace - Powered by CSpace