Local features and contextual dependencies are crucial for 3D point cloud analysis. Many works have been devoted to designing better local convolutional kernels that exploit the contextual dependencies. However, current point convolutions lack robustness to varying point cloud density. Moreover, contextual modeling is dominated by non-local or self-attention models which are computationally expensive. To solve these problems, we propose density adaptive convolution, coined DAConv. The key idea is to adaptively learn the convolutional weights from geometric connections obtained from the point density and position. To extract precise context dependencies with fewer computations, we propose an interactive attention module (IAM) that embeds spatial information into channel attention along different spatial directions. DAConv and IAM are integrated in a hierarchical network architecture to achieve local density and contextual direction-aware learning for point cloud analysis. Experiments show that DAConv is significantly more robust to point density compared to existing methods and extensive comparisons on challenging 3D point cloud datasets show that our network achieves state-of-the-art classification results of 93.6% on ModelNet40, competitive semantic segmentation results of 68.71% mIoU on S3DIS and part segmentation results of 86.7% mIoU on ShapeNet.

翻译：摘要：局部特征和上下文依赖关系对于三维点云分析至关重要。许多研究致力于设计能有效利用上下文依赖关系的局部卷积核。然而，现有点卷积方法对点云密度变化的鲁棒性不足。此外，上下文建模主要依赖非局部或自注意力模型，计算成本高昂。为解决上述问题，本文提出密度自适应卷积（DAConv），其核心思想是根据点密度与位置所获取的几何连接关系自适应学习卷积权重。为在较低计算量下提取精确的上下文依赖关系，我们提出交互式注意力模块（IAM），该模块沿不同空间方向将空间信息嵌入通道注意力。DAConv与IAM被集成于分层网络架构中，实现面向点云分析的局部密度与上下文方向感知学习。实验表明，相比现有方法，DAConv对点密度具有更强的鲁棒性；在挑战性三维点云数据集上的广泛对比显示，本网络在ModelNet40上取得93.6%的最优分类结果，在S3DIS上达到68.71% mIoU的竞争性语义分割性能，在ShapeNet上实现86.7% mIoU的部件分割结果。