Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds

06/05/2018
by   Pedro Hermosilla, et al.
8

We propose an efficient and effective method to learn convolutions for non-uniformly sampled point clouds, as they are obtained with modern acquisition techniques. Learning is enabled by four key novelties: first, representing the convolution kernel itself as a multilayer perceptron; second, phrasing convolution as a Monte Carlo integration problem, third, constructing an unstructured Poisson disk hierarchy for pooling, and fourth, using Monte Carlo convolution as pooling and upsampling operation at different resolutions simultaneously. The key idea across all these contributions is to guarantee adequate consideration of the underlying non-uniform sample distribution function from a Monte Carlo perspective. To make the proposed concepts applicable for real-world tasks, we furthermore propose an efficient implementation which significantly reduces the required GPU memory. By employing our method in hierarchical network architectures we can outperform most of the state-of-the-art networks on established point cloud segmentation, classification and normal estimation benchmarks. Furthermore, in contrast to most existing approaches, we can also demonstrate the robustness of our method with respect to sampling variations even when only trained on uniformly sampled models.

READ FULL TEXT

page 1

page 8

page 11

research
03/26/2021

PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

We introduce Position Adaptive Convolution (PAConv), a generic convoluti...
research
04/18/2019

KPConv: Flexible and Deformable Convolution for Point Clouds

We present Kernel Point Convolution (KPConv), a new design of point conv...
research
03/01/2020

PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling

Raw point clouds data inevitably contains outliers or noise through acqu...
research
03/24/2020

PointNetKL: Deep Inference for GICP Covariance Estimation in Bathymetric SLAM

Registration methods for point clouds have become a key component of man...
research
09/15/2017

Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks

We present a technique for efficiently synthesizing images of atmospheri...
research
01/19/2021

The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions

Recently, there has been a significant interest in performing convolutio...
research
01/10/2020

Efficient Programmable Random Variate Generation Accelerator from Sensor Noise

We introduce a method for non-uniform random number generation based on ...

Please sign up or login with your details

Forgot password? Click here to reset