Learning task-specific features for 3D pointcloud graph creation

09/02/2022
by   Elías Abad-Rocamora, et al.
0

Processing 3D pointclouds with Deep Learning methods is not an easy task. A common choice is to do so with Graph Neural Networks, but this framework involves the creation of edges between points, which are explicitly not related between them. Historically, naive and handcrafted methods like k Nearest Neighbors (k-NN) or query ball point over xyz features have been proposed, focusing more attention on improving the network than improving the graph. In this work, we propose a more principled way of creating a graph from a 3D pointcloud. Our method is based on performing k-NN over a transformation of the input 3D pointcloud. This transformation is done by an Multi-Later Perceptron (MLP) with learnable parameters that is optimized through backpropagation jointly with the rest of the network. We also introduce a regularization method based on stress minimization, which allows to control how distant is the learnt graph from our baseline: k-NN over xyz space. This framework is tested on ModelNet40, where graphs generated by our network outperformed the baseline by 0.3 points in overall accuracy.

READ FULL TEXT
research
10/11/2018

A Theory-Based Evaluation of Nearest Neighbor Models Put Into Practice

In the k-nearest neighborhood model (k-NN), we are given a set of points...
research
06/11/2018

A Fast and Easy Regression Technique for k-NN Classification Without Using Negative Pairs

This paper proposes an inexpensive way to learn an effective dissimilari...
research
03/25/2023

Spatio-Temporal driven Attention Graph Neural Network with Block Adjacency matrix (STAG-NN-BA)

Despite the recent advances in deep neural networks, standard convolutio...
research
02/25/2023

Random projection tree similarity metric for SpectralNet

SpectralNet is a graph clustering method that uses neural network to fin...
research
02/22/2023

Random Projection Forest Initialization for Graph Convolutional Networks

Graph convolutional networks (GCNs) were a great step towards extending ...
research
11/19/2022

GRATIS: Deep Learning Graph Representation with Task-specific Topology and Multi-dimensional Edge Features

Graph is powerful for representing various types of real-world data. The...
research
11/06/2020

Deep learning architectures for inference of AC-OPF solutions

We present a systematic comparison between neural network (NN) architect...

Please sign up or login with your details

Forgot password? Click here to reset