.png){kind=icon}
返回
Learning to Detect Good 3D Keypoints
.png){kind=icon}
PRE
AI
DOI：10.1007/s11263-017-1037-3.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The established approach to 3D keypoint detection consists in defining effective handcrafted saliency functions based on geometric cues with the aim of maximizing keypoint repeatability. Differently, the idea behind our work is to learn a descriptor-specific keypoint detector so as to optimize the end-to-end performance of the feature matching pipeline. Accordingly, we cast 3D keypoint detection as a classification problem between surface patches that can or cannot be matched correctly by a given 3D descriptor, i.e. those either good or not in respect to that descriptor. We propose a machine learning framework that allows for defining examples of good surface patches from the training data and leverages Random Forest classifiers to realize both fixed-scale and adaptive-scale 3D keypoint detectors. Through extensive experiments on standard datasets, we show how feature matching performance improves significantly by deploying 3D descriptors together with companion detectors learned by our methodology with respect to the adoption of established state-of-the-art 3D detectors based on hand-crafted saliency functions.
Keyword:
3D Keypoint Detection
3D Descriptors
Machine Learning
Surface Matching
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.3
论文数:
3.9K
被引数:
2.8W
机构
引用论文
Regulation of the p38 mitogen-activated protein kinase and dual-specificity phosphatase 1 feedback loop modulates the induction of interleukin 6 and 8 in cells infected with coronavirus infectious bronchitis virus.png)
Virology
OAAI
VirologyIF0
OAAI分享收藏Evaluation of 3D interest point detection techniques via human-generated ground truthVISUAL COMPUTER
VISUAL COMPUTERIF2.9
PREAI
分享收藏
Oral Idarubicin as a Single Agent Therapy in Patients with Relapsed or Resistant Multiple Myeloma
PREAI
分享收藏Repeated video head impulse testing in patients is a stable measure of the passive vestibulo-ocular reflex对患者进行重复的视频头冲动测试是对被动前庭眼反射的稳定测量OAAI
OAAI分享收藏Quantitative assessment of global cerebral metabolic rate of oxygen (CMRO2) in neonates using MRIOAAI
OAAI分享收藏
查看更多内容