Full Point Encoding for Local Feature Aggregation in 3D Point Clouds

by   Yong He, et al.

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 6-fold and 72.2


page 1

page 5

page 7

page 8

page 10


Multi-scale Network with Attentional Multi-resolution Fusion for Point Cloud Semantic Segmentation

In this paper, we present a comprehensive point cloud semantic segmentat...

IC classifier: a classifier for 3D industrial components based on geometric prior using GNN

In this paper, we propose an approach to address the problem of classify...

3DLG-Detector: 3D Object Detection via Simultaneous Local-Global Feature Learning

Capturing both local and global features of irregular point clouds is es...

Extracting Parts of 2D Shapes Using Local and Global Interactions Simultaneously

Perception research provides strong evidence in favor of part based repr...

Two Heads are Better than One: Geometric-Latent Attention for Point Cloud Classification and Segmentation

We present an innovative two-headed attention layer that combines geomet...

Context-Aware Transformer for 3D Point Cloud Automatic Annotation

3D automatic annotation has received increased attention since manually ...

Point Transformer

In this work, we present Point Transformer, a deep neural network that o...

Please sign up or login with your details

Forgot password? Click here to reset