Log In Sign Up

Interpolated Convolutional Networks for 3D Point Cloud Understanding

by   Jiageng Mao, et al.

Point cloud is an important type of 3D representation. However, directly applying convolutions on point clouds is challenging due to the sparse, irregular and unordered data structure. In this paper, we propose a novel Interpolated Convolution operation, InterpConv, to tackle the point cloud feature learning and understanding problem. The key idea is to utilize a set of discrete kernel weights and interpolate point features to neighboring kernel-weight coordinates by an interpolation function for convolution. A normalization term is introduced to handle neighborhoods of different sparsity levels. Our InterpConv is shown to be permutation and sparsity invariant, and can directly handle irregular inputs. We further design Interpolated Convolutional Neural Networks (InterpCNNs) based on InterpConv layers to handle point cloud recognition tasks including shape classification, object part segmentation and indoor scene semantic parsing. Experiments show that the networks can capture both fine-grained local structures and global shape context information effectively. The proposed approach achieves state-of-the-art performance on public benchmarks including ModelNet40, ShapeNet Parts and S3DIS.


page 7

page 8


Global Context Aware Convolutions for 3D Point Cloud Understanding

Recent advances in deep learning for 3D point clouds have shown great pr...

PointConv: Deep Convolutional Networks on 3D Point Clouds

Unlike images which are represented in regular dense grids, 3D point clo...

CKConv: Learning Feature Voxelization for Point Cloud Analysis

Despite the remarkable success of deep learning, optimal convolution ope...

Differentiable Convolution Search for Point Cloud Processing

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

Density-Aware Convolutional Networks with Context Encoding for Airborne LiDAR Point Cloud Classification

To better address challenging issues of the irregularity and inhomogenei...

Deep Parametric Continuous Convolutional Neural Networks

Standard convolutional neural networks assume a grid structured input is...

Structured Sparse Convolutional Autoencoder

This paper aims to improve the feature learning in Convolutional Network...