Most prior work represents the shapes of point clouds by coordinates. However, it is
insufficient to describe the local geometry directly. In this paper, we present RepSurf …

Convolution on 3D point clouds that generalized from 2D grid-like domains is widely
researched yet far from perfect. The standard convolution characterises feature …

The prevalence of relation networks in computer vision is in stark contrast to underexplored
point-based methods. In this paper, we explore the possibilities of local relation operators …

Feature representation learning is a key component in 3D point cloud analysis. However,
the powerful convolutional neural networks (CNNs) cannot be applied due to the irregular …

We consider the deep point cloud analysis tasks where the inputs of the networks are
randomly rotated. Recent progress in rotation-invariant point cloud analysis is mainly driven …

Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep
learning. The traditional wisdom of convolution characterises feature correspondences …

Point clouds have garnered increasing research attention and found numerous practical
applications. However, many of these applications, such as autonomous driving and robotic …

We consider the attributes of a point cloud as samples of a vector-valued volumetric function
at discrete positions. To compress the attributes given the positions, we compress the …

Remarkable performance from Transformer networks in Natural Language Processing
promote the development of these models in dealing with computer vision tasks such as …

In recent years, neural implicit representations have made remarkable progress in modeling
of 3D shapes with arbitrary topology. In this work, we address two key limitations of such …