arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1810.08950cs.CV
收藏

三维曲面上学习谱变换网络的非刚性形状分析

Learning Spectral Transform Network on 3D Surface for Non-rigid Shape Analysis

Xi’an Jiaotong University(西安交通大学)

Ruixuan Yu, Jian Sun, Huibin Li

摘要:

在三维曲面上设计用于非刚性形状分析的网络是一项具有挑战性的任务。在这项工作中,我们提出了一种新的光谱变换网络的3D表面上学习形状描述符。建议的网络架构包括四个阶段:原始描述符提取,表面二阶池,混合基于幂函数的谱变换,和度量学习。所提出的网络简单而浅层。在具有挑战性的基准上的定量实验表明了其对非刚性形状检索和分类的有效性,例如,它在SHREC 14,15数据集以及SHREC 17数据集的Range子集上实现了最高的准确度。

英文摘要:

Designing a network on 3D surface for non-rigid shape analysis is a challenging task. In this work, we propose a novel spectral transform network on 3D surface to learn shape descriptors. The proposed network architecture consists of four stages: raw descriptor extraction, surface second-order pooling, mixture of power function-based spectral transform, and metric learning. The proposed network is simple and shallow. Quantitative experiments on challenging benchmarks show its effectiveness for non-rigid shape retrieval and classification, e.g., it achieved the highest accuracies on SHREC14, 15 datasets as well as the Range subset of SHREC17 dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑