Recently, many deep neural networks were designed to process 3D point clouds, but a common drawback is that rotation invariance is not ensured, leading to poor generalization to arbitrary orientations. In this paper, we introduce a new low-level purely rotation-invariant representation to replace common 3D Cartesian coordinates as the network inputs. Also, we present a network architecture to embed these representations into features, encoding local relations between points and their neighbors, and the global shape structure. To alleviate inevitable global information loss caused by the rotation-invariant representations, we further introduce a region relation convolution to encode local and non-local information. We evaluate our method on multiple point cloud analysis tasks, including shape classification, part segmentation, and shape retrieval. Experimental results show that our method achieves consistent, and also the best performance, on inputs at arbitrary orientations, compared with the state-of-the-arts.
翻译:最近,许多深心神经网络被设计为处理3D点云,但一个共同的缺点是,轮换的偏差没有得到保证,导致对任意取向的概括化不力。在本文中,我们引入了一个新的低层次的纯轮换的偏差代表,以取代共同的 3D 笛卡尔坐标作为网络投入。此外,我们提出了一个网络架构,将这些表达方式嵌入特征中,将各点与其邻居之间的地方关系和全球形状结构编码。为了减轻轮换的偏差造成的不可避免的全球信息损失,我们进一步引入了一种区域关系演变以编码本地和非本地信息。我们评估了多点云分析任务的方法,包括形状分类、部分分割和形状检索。实验结果显示,我们的方法在任意取向的投入方面,与状态相比,取得了一致和最佳的成绩。