Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Learning 3D Keypoint Descriptors for Non-Rigid Shape Matching | |
Wang, Hanyu; Guo, Jianwei; Yan, Dong-Ming; Quan, Weize; Zhang, Xiaopeng | |
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 |
通讯作者 | Yan, Dong-Ming |
作者单位 | NLPR, Institute of Automation, Chinese Academy of Sciences |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Wang, Hanyu,Guo, Jianwei,Yan, Dong-Ming,et al. Learning 3D Keypoint Descriptors for Non-Rigid Shape Matching[C],2018. |
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 | ||
2018_ECCV_keypoint.p(4072KB) | 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