论文标题
基于体素的3D对象分类的快速混合级联网络
A Fast Hybrid Cascade Network for Voxel-based 3D Object Classification
论文作者
论文摘要
近年来，基于体素的3D对象分类已经进行了彻底研究。大多数以前的方法将经典的2D卷积转换为3D形式，将进一步应用于具有二进制体素表示的对象进行分类。但是，在许多情况下，二元体素表示对于3D卷积不是很有效。在本文中，我们为基于体素的3D对象分类的混合级联体系结构提出了一个混合级联体系结构。它由三个阶段组成，该阶段分别由完全连接和卷积层组成，分别涉及简单，中等和硬的3D模型。我们提出的方法可以平衡准确性和速度。通过给每个体素一个签名的距离值，可以观察到有关准确性的明显增益。此外，与最新的点云和基于体素的方法相比，平均推理时间可以大大加速。
Voxel-based 3D object classification has been thoroughly studied in recent years. Most previous methods convert the classic 2D convolution into a 3D form that will be further applied to objects with binary voxel representation for classification. However, the binary voxel representation is not very effective for 3D convolution in many cases. In this paper, we propose a hybrid cascade architecture for voxel-based 3D object classification. It consists of three stages composed of fully connected and convolutional layers, dealing with easy, moderate, and hard 3D models respectively. Both accuracy and speed can be balanced in our proposed method. By giving each voxel a signed distance value, an obvious gain regarding the accuracy can be observed. Besides, the mean inference time can be speeded up hugely compared with the state-of-the-art point cloud and voxel based methods.
