3DTNet: Learning Local Features using 2D and 3D Cues | |
Xing, Xiaoxia1,2; Cai, Yinghao1; Lu, Tao1; Cai, Shaojun3; Yang, Yiping1; Wen, Dayong1 | |
2018-09 | |
会议名称 | 3D Vision |
会议日期 | Sep 5-8, 2019 |
会议地点 | Verona, Italy |
摘要 | We present an approach to learn 3D local descriptor by combining both 2D texture and 3D geometric information, which can be used to register partial 3D data for a variety of vision applications. Unlike previous approaches which simply concatenate features learned from multiple sources into one feature descriptor, we learn 2D and 3D feature representations jointly. We design a network, 3DTNet with an architecture particularly designed for learning robust local feature representation leveraging both texture and geometric information. Two types of information are interacted with each other which results in more robust and stable feature representation. Finally, feature representations of multi-scale neighborhoods are aggregated to further improve the performance of feature matching. Extensive experimental results show that our method outperforms state-of-art 2D or 3D descriptors in terms of both accuracy and efficiency. |
关键词 | 2D-3D fusion Local feature |
DOI | 10.1109/3DV.2018.00057 |
收录类别 | EI |
语种 | 英语 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48783 |
专题 | 综合信息系统研究中心_视知觉融合及其应用 毕业生 |
通讯作者 | Xing, Xiaoxia |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences, Beijing, China 2.University of Chinese Academy of Sciences, Beijing, China 3.UISEE Technologies Beijing Co., Ltd |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Xing, Xiaoxia,Cai, Yinghao,Lu, Tao,et al. 3DTNet: Learning Local Features using 2D and 3D Cues[C],2018. |
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 | ||
3DTNet_Learning_Loca(3848KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论