中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Robust 3D reconstruction from uncalibrated small motion clips

文献类型：期刊论文

作者Li, Zhaoxin2; Zuo, Wangmeng3; Wang, Zhaoqi2; Zhang, Lei1
刊名VISUAL COMPUTER
出版日期2021-03-12
页码17
关键词3D reconstruction Small motion Multi-view stereo Line segment PatchMatch stereo
ISSN号0178-2789
DOI10.1007/s00371-021-02090-w
英文摘要Small motion can be induced from burst video clips captured by a handheld camera when the shutter button is pressed. Although uncalibrated burst video clip conveys valuable parallax information, it generally has small baseline between frames, making it difficult to reconstruct 3D scenes. Existing methods usually employ a simplified camera parameterization process with keypoint-based structure from small motion (SFSM), followed by a tailored dense reconstruction. However, such SFSM methods are sensitive to insufficient or unreliable keypoint features, and the subsequent dense reconstruction may fail to recover the detailed surface. In this paper, we propose a robust 3D reconstruction pipeline by leveraging both keypoint and line segment features from video clips to alleviate the uncertainty induced by small baseline. A joint feature-based structure from small motion method is first presented to improve the robustness of the self-calibration with line segment constraints, and then, a noise-aware PatchMatch stereo module is proposed to improve the accuracy of the dense reconstruction. Finally, a confidence weighted fusion process is utilized to further suppress depth noise and mitigate erroneous depth. The proposed method can reduce the failure cases of self-calibration when the keypoints are insufficient, while recovering the detailed 3D surfaces. In comparison with state of the arts, our method achieves more robust and accurate 3D reconstruction results for a variety of challenging scenes.
资助项目National Key Research and Development Program of China[2018AAA0103002] ; National Natural Science Foundation of China[61702482]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000628071600001
出版者SPRINGER
源URL[http://119.78.100.204/handle/2XEOYT63/16900]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Li, Zhaoxin
作者单位1.Hong Kong Polytech Univ, Dept Comp, Kowloon, Hong Kong, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
3.Harbin Inst Technol, Sch Comp Sci & Technol, Harbin, Peoples R China
推荐引用方式
GB/T 7714		 Li, Zhaoxin,Zuo, Wangmeng,Wang, Zhaoqi,et al. Robust 3D reconstruction from uncalibrated small motion clips[J]. VISUAL COMPUTER,2021:17.
APA Li, Zhaoxin,Zuo, Wangmeng,Wang, Zhaoqi,&Zhang, Lei.(2021).Robust 3D reconstruction from uncalibrated small motion clips.VISUAL COMPUTER,17.
MLA Li, Zhaoxin,et al."Robust 3D reconstruction from uncalibrated small motion clips".VISUAL COMPUTER (2021):17.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

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。