首页|A Unified Feature Representation and Learning Framework for 3D Shape

A Unified Feature Representation and Learning Framework for 3D Shape

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
  • 维普
In conventional 3D shape retrieval and classification,they differentiate each other in their final stages.We propose a unified feature representation and learning framework for the instance-based shape retrieval and classification.Firstly,we render every 3D model in several directions and use the produced view-sets to represent the 3D models.In this way,both tasks can be tackled by measuring the distances between rendered views of 3D models.Secondly,we construct the view-sets as Symmetric positive definite matrices (SPDMs),which are points on a Riemannian manifold.Thus,the shape retrieval and classification tasks are reduced to a problem of measuring the distances between projected views and SPDMs.To solve this heterogeneous problem,we map them to a Hilbert space using a method of point-to-set matching.In this Hilbert space,the distances are surprisingly easy to calculate.Finally,we use a robust nearest-neighbor approach to unify the instance-based shape retrieval and classification.Our framework combines the state-of-the-art deep learning approaches with traditional mathematical optimization method,makes full use of both advantages,which is much more flexible than pure deep learning methods.Experimental results show the efficiency of our approach.

Shape retrievalShape classificationDeep learningEuclidean spaceRiemannian manifoldHilbert spaceMetric learning

MU Panpan、ZHANG Sanyuan、PAN Xiang、HONG Zhenjie

展开 >

Art Design College, Zhejiang Gongshang University, Hangzhou 310018, China

College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China

College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China

School of Mathematics and Information Science, Wenzhou University, Wenzhou 325027, China

展开 >

This work is supported by the National Natural Science Foundation of ChinaNatural Science Foundation of Zhejiang ProvinceNatural Science Foundation of Zhejiang Province

61871258LQ16F020007LY19F020031

2019

10.1049/cje.2019.06.019

中国电子杂志(英文版)

中国电子杂志(英文版)

CSTPCDCSCDSCIEI
ISSN：1022-4653
年,卷(期)：2019.28(5)
  • 21