面向三维模型视图特征提取的残差卷积网络优化

在已有残差卷积神经网络基础上,采用加权损失函数提高视图特征的可分性,提出面向三维模型视图特征提取的残差卷积网络优化算法.首先对三维模型进行多视图渲染得到二维视图;然后通过残差网络扩展模块加深网络深度;最后采用中心损失函数和交叉熵损失函数定义加权损失函数,解决交叉熵损失函数因为类内距离小于类间距离而导致的特征不可分问题.在ModelNet数据集上的实验结果表明,该算法提取到的特征在三维模型分类问题上性能表现优异.

Residual Convolution Network Optimization for View Features Extraction of 3D Model

On the basis of the existing residual convolutional neural networks, the weighted loss function is used to improve the discriminability of the view features of 3D models. A new view feature extraction algorithm of 3D models is proposed to optimize the residual convolutional networks. Firstly, a 3D model is rendered to obtain different views. Then, a residual network expansion module is used to increase depth of the network. Meanwhile, a weighted loss function is defined by combining the center loss function and the cross entropy loss function. As a result, it can solve the problem that the intra-class distance is less than the inter-class distance. Experiments on ModelNet datasets show that the algorithm’s performance is excellent in 3D model classification.