Large-Scale Shape Retrieval with Sparse 3D Convolutional Neural Networks

TL;DR

This paper evaluates S3DCNN, a sparse 3D CNN, on large-scale shape retrieval tasks, showing comparable accuracy to state-of-the-art methods with reduced computational costs, and discusses the impact of input resolution on performance.

Contribution

The paper provides a performance evaluation of S3DCNN on ModelNet40, highlighting its efficiency and analyzing how input voxel resolution affects shape classification and retrieval.

Findings

S3DCNN achieves similar accuracy to state-of-the-art models.

Higher input resolution offers limited benefits due to generalization constraints.

Reduced computational costs in training and inference.

Abstract

In this paper we present results of performance evaluation of S3DCNN - a Sparse 3D Convolutional Neural Network - on a large-scale 3D Shape benchmark ModelNet40, and measure how it is impacted by voxel resolution of input shape. We demonstrate comparable classification and retrieval performance to state-of-the-art models, but with much less computational costs in training and inference phases. We also notice that benefits of higher input resolution can be limited by an ability of a neural network to generalize high level features.