Ensemble of PANORAMA-based convolutional neural networks for 3D model classification and retrieval
Ensemble of PANORAMA-based convolutional neural networks for 3D model classification and retrieval
复制标题
DOI：
10.1016/j.cag.2017.12.001
复制
发表时间：
2018-04-01
影响因子：
2.5
通讯作者：
Theoharis, Theoharis
中科院分区：
文献类型：
--
作者：
Sfikas, Konstantinos;Pratikakis, Ioannis;Theoharis, Theoharis
提出了一种用于3D模型分类和检索的新方法;它利用3D模型的2D全景视图表示作为卷积神经网络集成的输入，该集成自动计算特征。所提出的管道的第一步，姿势归一化使用SYMPAN方法执行，该方法也在全景视图表示上计算。在训练阶段，对应于主轴的三个全景视图用于训练卷积神经网络的集合。全景视图由3通道图像组成，包含空间分布图、法线偏差图和法线偏差图梯度图像的幅度。该方法的目的是捕捉特征的连续性的3D模型，同时通过构建一个增强的图像表示最大限度地减少数据预处理。它在两个标准的大规模数据集上进行了广泛的分类和检索准确性测试：ModelNet和ShapeNet。(C)2017爱思唯尔有限公司版权所有
A novel method for the classification and retrieval of 3D models is proposed; it exploits the 2D panoramic view representation of 3D models as input to an ensemble of convolutional neural networks which automatically compute the features. The first step of the proposed pipeline, pose normalization is performed using the SYMPAN method, which is also computed on the panoramic view representation. In the training phase, three panoramic views corresponding to the major axes, are used for the training of an ensemble of convolutional neural networks. the panoramic views consist of 3-channel images, containing the Spatial Distribution Map, the Normals' Deviation Map and the magnitude of the Normals' Devation Map Gradient Image. The proposed method aims at capturing feature continuity of 3D models, while simultaneously minimizing data preprocessing via the construction of an augmented image representation. It is extensively tested in terms of classification and retrieval accuracy on two standard large scale datasets: ModelNet and ShapeNet. (C) 2017 Elsevier Ltd. All rights reserved.