Flex-Convolution (Deep Learning Beyond Grid-Worlds)

03/20/2018
by   Fabian Groh, et al.
0

The goal of this work is to enable deep neural networks to learn representations for irregular 3D structures -- just like in common approaches for 2D images. Unfortunately, current network primitives such as convolution layers are specifically designed to exploit the natural data representation of images -- a fixed and regular grid structure. This represents a limitation when transferring these techniques to more unstructured data like 3D point clouds or higher dimensional data. In this work, we propose a surprisingly natural generalization flex-convolution of the conventional convolution layer and provide a highly efficient implementation. Compared to very specific neural network architectures for point cloud processing, our more generic approach yields competitive results on the rather small standard benchmark sets using fewer parameters and lower memory consumption. Our design even allows for raw neural networks prediction on several magnitudes larger point clouds, providing superior results compared to previous hand-tuned and well-engineered approaches on the 2D-3D-S dataset.

READ FULL TEXT

page 6

page 14

research
11/29/2021

diffConv: Analyzing Irregular Point Clouds with an Irregular View

Standard spatial convolutions assume input data with a regular neighborh...
research
06/08/2018

RGCNN: Regularized Graph CNN for Point Cloud Segmentation

Point cloud, an efficient 3D object representation, has become popular w...
research
12/04/2019

Deep Morphological Hit-or-Miss Transform Neural Network

Neural networks have demonstrated breakthrough results in numerous appli...
research
12/05/2020

ParaNet: Deep Regular Representation for 3D Point Clouds

Although convolutional neural networks have achieved remarkable success ...
research
05/21/2018

Spherical Convolutional Neural Network for 3D Point Clouds

We propose a neural network for 3D point cloud processing that exploits ...
research
10/14/2019

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

To better address challenging issues of the irregularity and inhomogenei...
research
01/15/2021

DeepWaste: Applying Deep Learning to Waste Classification for a Sustainable Planet

Accurate waste disposal, at the point of disposal, is crucial to fightin...

Please sign up or login with your details

Forgot password? Click here to reset