Point cloud processing methods exploit local point features and global context through aggregation which does not explicity model the internal correlations between local and global features. To address this problem, we propose full point encoding which is applicable to convolution and transformer architectures. Specifically, we propose Full Point Convolution (FPConv) and Full Point Transformer (FPTransformer) architectures. The key idea is to adaptively learn the weights from local and global geometric connections, where the connections are established through local and global correlation functions respectively. FPConv and FPTransformer simultaneously model the local and global geometric relationships as well as their internal correlations, demonstrating strong generalization ability and high performance. FPConv is incorporated in classical hierarchical network architectures to achieve local and global shape-aware learning. In FPTransformer, we introduce full point position encoding in self-attention, that hierarchically encodes each point position in the global and local receptive field. We also propose a shape aware downsampling block which takes into account the local shape and the global context. Experimental comparison to existing methods on benchmark datasets show the efficacy of FPConv and FPTransformer for semantic segmentation, object detection, classification, and normal estimation tasks. In particular, we achieve state-of-the-art semantic segmentation results of 76% mIoU on S3DIS 6-fold and 72.2% on S3DIS Area5.
翻译:云点处理方法通过聚合利用本地点特点和全球背景,而合并并不明确模型当地和全球特征之间的内部关联。为了解决这一问题,我们提议了适用于进化和变压结构的全点编码。具体地说,我们提议了全点革命(FP Conv)和全点变换器(FP Transfer)结构。关键思想是适应性地学习当地和全球几何连接的权重,这些连接分别通过地方和全球相关功能建立。FP Conv和FPTransformex同时模拟当地和全球几何关系及其内部关联,显示强大的通用能力和高性能。FPConv被纳入传统的等级网络结构结构,以实现本地和全球的元化学习。在FPConv和全点变换器结构中,我们引入了自我注意的全点位置编码,分级地编码了全球和本地的每个点位置。我们还提议了一个有意识的下游块块块,其中考虑到当地形状和全球背景。在基准数据集方面的实验性比较中,显示SFPConv和FTrial3区域检测结果部分的效能。Strax-sealtraction3,我们实现Sal-sealtraxal-se分类的Straction的Straction-seal-se-se-sealtraction。</s>