Directionally Convolutional Networks for 3D Shape Segmentation
Directionally Convolutional Networks for 3D Shape Segmentation
复制标题
DOI：
10.1109/iccv.2017.294
复制
发表时间：
2017-10
期刊：
影响因子：
--
通讯作者：
Haotian Xu;Ming Dong;Z. Zhong
中科院分区：
文献类型：
--
作者：
Haotian Xu;Ming Dong;Z. Zhong
以前的三维形状分割方法主要依赖于启发式处理和手动调整的几何描述符。在本文中，我们提出了一种新的三维形状表示学习方法，方向卷积网络（DCN），解决形状分割问题。DCN将卷积运算从图像扩展到3D形状的表面网格。使用DCN，我们从原始几何特征中学习有效的形状表示，即，面部法线和距离，以实现鲁棒分割。更具体地说，提出了一个双流分割框架：一个流是由建议的DCN与人脸法线作为输入，和其他流是由神经网络与人脸距离直方图作为输入实现。从两个流中学习的形状表示通过逐元素乘积融合。最后，利用条件随机场（CRF）对分割结果进行优化。通过在基准数据集上进行的大量实验，我们证明了我们的方法在各种各样的3D形状上都优于当前最先进的方法（包括经典的和基于深度学习的）。
Previous approaches on 3D shape segmentation mostly rely on heuristic processing and hand-tuned geometric descriptors. In this paper, we propose a novel 3D shape representation learning approach, Directionally Convolutional Network (DCN), to solve the shape segmentation problem. DCN extends convolution operations from images to the surface mesh of 3D shapes. With DCN, we learn effective shape representations from raw geometric features, i.e., face normals and distances, to achieve robust segmentation. More specifically, a two-stream segmentation framework is proposed: one stream is made up by the proposed DCN with the face normals as the input, and the other stream is implemented by a neural network with the face distance histogram as the input. The learned shape representations from the two streams are fused by an element-wise product. Finally, Conditional Random Field (CRF) is applied to optimize the segmentation. Through extensive experiments conducted on benchmark datasets, we demonstrate that our approach outperforms the current state-of-the-arts (both classic and deep learning-based) on a large variety of 3D shapes.