Survey and Evaluation of Neural 3D Shape Classification Approaches

Martin Mirbauer Miroslav Krabec Jaroslav Křivánek Elena Šikudová
Charles University, Faculty of Mathematics and Physics, Prague, Czech Republic
Chaos Czech a.s., Prague, Czech Republic

Abstract

Classification of 3D objects – the selection of a category in which each object belongs – is of great interest in the field of machine learning. Numerous researchers use deep neural networks to address this problem, altering the network architecture and representation of the 3D shape used as an input. To investigate the effectiveness of their approaches, we conduct an extensive survey of existing methods and identify common ideas by which we categorize them into a taxonomy. Second, we evaluate 11 selected classification networks on two 3D object datasets, extending the evaluation to a larger dataset on which most of the selected approaches have not been tested yet. For this, we provide a framework for converting shapes from common 3D mesh formats into formats native to each network, and for training and evaluating different classification approaches on this data. Despite being partially unable to reach the accuracies reported in the original papers, we compare the relative performance of the approaches as well as their performance when changing datasets as the only variable to provide valuable insights into performance on different kinds of data. We make our code available to simplify running training experiments with multiple neural networks with different prerequisites.

Reference

@ARTICLE{9515991,
  author={Mirbauer, Martin and Krabec, Miroslav and Křivánek, Jaroslav and Šikudová, Elena},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
  title={Survey and Evaluation of Neural 3D Shape Classification Approaches}, 
  year={2022},
  volume={44},
  number={11},
  pages={8635-8656},
  doi={10.1109/TPAMI.2021.3102676}}

Links and Downloads

Paper fulltext
(acceped version)		 Supplementary material document Framework code and manual Manual ShapenetCore v2
train/test/val split
paper thumbnail supplementary material thumbnail code thumbnail manual thumbnail train/test split thumbnail
PDF (1.5 MB) PDF (1.3 MB) ZIP (500 kB) HTML CSV (2.4 MB)

Download the published version of the paper on the publisher's website.
Paper's page on our new website.

Acknowledgments

This work was supported by the Charles University Grant Agency project GAUK 966119. This work was supported by the Charles University grant SVV-260588. This work was supported by the Grant Schemes at CU, reg. no. CZ.02.2.69/0.0/0.0/19_073/0016935.