CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
HSfM: Hybrid Structure-from-Motion
Cui Hainan(崔海楠); Xiang Gao(高翔); Shen Shuhan(申抒含); Hu Zhanyi(胡占义)
2017
会议名称Conference on Computer Vision and Pattern Recognition
会议日期2017-06
会议地点USA,Honolulu
摘要
Structure-from-Motion (SfM) methods can be broadly
categorized as incremental or global according to their
ways to estimate initial camera poses. While incremental
system has advanced in robustness and accuracy, the ef-
ficiency remains its key challenge. To solve this problem,
global reconstruction system simultaneously estimates al-
l camera poses from the epipolar geometry graph, but it
is usually sensitive to outliers. In this work, we propose
a new hybrid SfM method to tackle the issues of efficien-
cy, accuracy and robustness in a unified framework. More
specifically, we propose an adaptive community-based ro-
tation averaging method first to estimate camera rotations
in a global manner. Then, based on these estimated camera
rotations, camera centers are computed in an incremental
way. Extensive experiments show that our hybrid method
performs similarly or better than many of the state-of-the-
art global SfM approaches, in terms of computational effi-
ciency, while achieves similar reconstruction accuracy and
robustness with two other state-of-the-art incremental SfM
approaches
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/19765
专题模式识别国家重点实验室_机器人视觉
推荐引用方式
GB/T 7714
Cui Hainan,Xiang Gao,Shen Shuhan,et al. HSfM: Hybrid Structure-from-Motion[C],2017.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Cui_HSfM_Hybrid_Stru(3023KB)会议论文 开放获取CC BY-NC-SA浏览 请求全文
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
[Cui Hainan(崔海楠)]的文章
[Xiang Gao(高翔)]的文章
[Shen Shuhan(申抒含)]的文章
百度学术
百度学术中相似的文章
[Cui Hainan(崔海楠)]的文章
[Xiang Gao(高翔)]的文章
[Shen Shuhan(申抒含)]的文章
必应学术
必应学术中相似的文章
[Cui Hainan(崔海楠)]的文章
[Xiang Gao(高翔)]的文章
[Shen Shuhan(申抒含)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Cui_HSfM_Hybrid_Structure-from-Motion_CVPR_2017_paper (2).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。