Deep Parametric Continuous Convolutional Neural Networks

Abstract

Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we propose Parametric Continuous Convolution, a new learnable operator that operates over non-grid structured data. The key idea is to exploit parameterized kernel functions that span the full continuous vector space. This generalization allows us to learn over arbitrary data structures as long as their support relationship is computable. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes, and lidar motion estimation of driving scenes.

Accepted by CVPR 2018

References in corpus (1)

• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

Cited by in corpus (5)

• Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling
• PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis
• Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor Scene
• PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution
• Continuous Conditional Random Field Convolution for Point Cloud Segmentation