DeepAI AI Chat
Log In Sign Up

Learning Graph-Convolutional Representations for Point Cloud Denoising

by   Francesca Pistilli, et al.
Politecnico di Torino

Point clouds are an increasingly relevant data type but they are often corrupted by noise. We propose a deep neural network based on graph-convolutional layers that can elegantly deal with the permutation-invariance problem encountered by learning-based point cloud processing methods. The network is fully-convolutional and can build complex hierarchies of features by dynamically constructing neighborhood graphs from similarity among the high-dimensional feature representations of the points. When coupled with a loss promoting proximity to the ideal surface, the proposed approach significantly outperforms state-of-the-art methods on a variety of metrics. In particular, it is able to improve in terms of Chamfer measure and of quality of the surface normals that can be estimated from the denoised data. We also show that it is especially robust both at high noise levels and in presence of structured noise such as the one encountered in real LiDAR scans.


RGCNN: Regularized Graph CNN for Point Cloud Segmentation

Point cloud, an efficient 3D object representation, has become popular w...

3D Point Cloud Denoising via Deep Neural Network based Local Surface Estimation

We present a neural-network-based architecture for 3D point cloud denois...

The Perfect Match: 3D Point Cloud Matching with Smoothed Densities

We propose 3DSmoothNet, a full workflow to match 3D point clouds with a ...

Point Cloud Denoising via Momentum Ascent in Gradient Fields

To achieve point cloud denoising, traditional methods heavily rely on ge...

Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling

Fully exploring correlation among points in point clouds is essential fo...

A method of limiting performance loss of CNNs in noisy environments

Convolutional Neural Network (CNN) recognition rates drop in the presenc...