Learning 3D Keypoint Descriptors for Non-Rigid Shape Matching
Hanyu Wang; Jianwei Guo; Dong-Ming Yan; Weize Quan; Xiaopeng Zhang
2018-09
会议名称15th European Conference on Computer Vision (ECCV)
会议日期September 8 – 14, 2018
会议地点Munich, Germany
摘要
In this paper, we present a novel deep learning framework
that derives discriminative local descriptors for 3D surface shapes. In
contrast to previous convolutional neural networks (CNNs) that rely on
rendering multi-view images or extracting intrinsic shape properties, we
parameterize the multi-scale localized neighborhoods of a keypoint into
regular 2D grids, which are termed as ‘geometry images’. The benefits of
such geometry images include retaining sufficient geometric information,
as well as allowing the usage of standard CNNs. Specifically, we leverage
a triplet network to perform deep metric learning, which takes a set of
triplets as input, and a newly designed triplet loss function is minimized
to distinguish between similar and dissimilar pairs of keypoints. At the
testing stage, given a geometry image of a point of interest, our network
outputs a discriminative local descriptor for it. Experimental results for
non-rigid shape matching on several benchmarks demonstrate the superior
performance of our learned descriptors over traditional descriptors
and the state-of-the-art learning-based alternatives.
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/21688
专题模式识别国家重点实验室_多媒体计算与图形学
通讯作者Dong-Ming Yan
作者单位NLPR, Institute of Automation, Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Hanyu Wang,Jianwei Guo,Dong-Ming Yan,et al. Learning 3D Keypoint Descriptors for Non-Rigid Shape Matching[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
2018_ECCV_keypoint.p(4072KB)会议论文 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
[Hanyu Wang]的文章
[Jianwei Guo]的文章
[Dong-Ming Yan]的文章
百度学术
百度学术中相似的文章
[Hanyu Wang]的文章
[Jianwei Guo]的文章
[Dong-Ming Yan]的文章
必应学术
必应学术中相似的文章
[Hanyu Wang]的文章
[Jianwei Guo]的文章
[Dong-Ming Yan]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 2018_ECCV_keypoint.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。