# Momen(e)t: Flavor the Moments in Learning to Classify Shapes

## TL;DR

This paper introduces a novel neural network approach that incorporates shape moments through polynomial coordinate functions, achieving state-of-the-art results in 3D shape classification efficiently.

## Contribution

It extends existing point cloud classification methods by integrating higher order shape moments, improving accuracy and efficiency.

## Key findings

- Achieves state-of-the-art classification accuracy on benchmarks.
- Reduces memory and computational requirements.
- Effectively captures higher order shape features.

## Abstract

A fundamental question in learning to classify 3D shapes is how to treat the data in a way that would allow us to construct efficient and accurate geometric processing and analysis procedures. Here, we restrict ourselves to networks that operate on point clouds. There were several attempts to treat point clouds as non-structured data sets by which a neural network is trained to extract discriminative properties. The idea of using 3D coordinates as class identifiers motivated us to extend this line of thought to that of shape classification by comparing attributes that could easily account for the shape moments. Here, we propose to add polynomial functions of the coordinates allowing the network to account for higher order moments of a given shape. Experiments on two benchmarks show that the suggested network is able to provide state of the art results and at the same token learn more efficiently in terms of memory and computational complexity.