Dynamic Graph CNN for Learning on Point Clouds

by   Yongbin Sun, et al.

Point clouds provide a flexible and scalable geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. Hence, the design of intelligent computational models that act directly on point clouds is critical, especially when efficiency considerations or noise preclude the possibility of expensive denoising and meshing procedures. While hand-designed features on point clouds have long been proposed in graphics and vision, however, the recent overwhelming success of convolutional neural networks (CNNs) for image analysis suggests the value of adapting insight from CNN to the point cloud world. To this end, we propose a new neural network module dubbed EdgeConv suitable for CNN-based high-level tasks on point clouds including classification and segmentation. EdgeConv is differentiable and can be plugged into existing architectures. Compared to existing modules operating largely in extrinsic space or treating each point independently, EdgeConv has several appealing properties: It incorporates local neighborhood information; it can be stacked or recurrently applied to learn global shape properties; and in multi-layer systems affinity in feature space captures semantic characteristics over potentially long distances in the original embedding. Beyond proposing this module, we provide extensive evaluation and analysis revealing that EdgeConv captures and exploits fine-grained geometric properties of point clouds. The proposed approach achieves state-of-the-art performance on standard benchmarks including ModelNet40 and S3DIS.


page 6

page 10

page 12


PAI-Conv: Permutable Anisotropic Convolutional Networks for Learning on Point Clouds

Demand for efficient representation learning on point clouds is increasi...

Geometric Feedback Network for Point Cloud Classification

As the basic task of point cloud learning, classification is fundamental...

ODFNet: Using orientation distribution functions to characterize 3D point clouds

Learning new representations of 3D point clouds is an active research ar...

A Convolutional Architecture for 3D Model Embedding

During the last years, many advances have been made in tasks like3D mode...

CP^3: Channel Pruning Plug-in for Point-based Networks

Channel pruning can effectively reduce both computational cost and memor...

Learning Inner-Group Relations on Point Clouds

The prevalence of relation networks in computer vision is in stark contr...

Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN

Recent advances in deep convolutional neural networks (CNNs) have motiva...

Please sign up or login with your details

Forgot password? Click here to reset