Log In Sign Up

DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing

by   Yongcheng Liu, et al.

Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable. A thorough grasp of the elusive shape requires sufficiently contextual semantic information, yet few works devote to this. Here we propose DensePoint, a general architecture to learn densely contextual representation for point cloud processing. Technically, it extends regular grid CNN to irregular point configuration by generalizing a convolution operator, which holds the permutation invariance of points, and achieves efficient inductive learning of local patterns. Architecturally, it finds inspiration from dense connection mode, to repeatedly aggregate multi-level and multi-scale semantics in a deep hierarchy. As a result, densely contextual information along with rich semantics, can be acquired by DensePoint in an organic manner, making it highly effective. Extensive experiments on challenging benchmarks across four tasks, as well as thorough model analysis, verify DensePoint achieves the state of the arts.


Relation-Shape Convolutional Neural Network for Point Cloud Analysis

Point cloud analysis is very challenging, as the shape implied in irregu...

Shape-Oriented Convolution Neural Network for Point Cloud Analysis

Point cloud is a principal data structure adopted for 3D geometric infor...

Differentiable Convolution Search for Point Cloud Processing

Exploiting convolutional neural networks for point cloud processing is q...


We present a simple and general framework for feature learning from poin...

Point is a Vector: A Feature Representation in Point Analysis

The irregularity and disorder of point clouds bring many challenges to p...

Point Cloud Processing via Recurrent Set Encoding

We present a new permutation-invariant network for 3D point cloud proces...