Structured 2D Representation of 3D Data for Shape Processing

TL;DR

This paper introduces a method to represent 3D shapes as structured 2D images, enabling the use of 2D CNNs for high-accuracy classification and segmentation of 3D data.

Contribution

It proposes a novel structured 2D representation of 3D shapes and demonstrates its effectiveness for both classification and segmentation tasks using 2D CNNs.

Findings

Achieved 99.7% accuracy on ModelNet40 classification

Improved state-of-the-art results significantly

Provided a new framework for 3D shape segmentation

Abstract

We represent 3D shape by structured 2D representations of fixed length making it feasible to apply well investigated 2D convolutional neural networks (CNN) for both discriminative and geometric tasks on 3D shapes. We first provide a general introduction to such structured descriptors, analyze their different forms and show how a simple 2D CNN can be used to achieve good classification result. With a specialized classification network for images and our structured representation, we achieve the classification accuracy of 99.7\% in the ModelNet40 test set - improving the previous state-of-the-art by a large margin. We finally provide a novel framework for performing the geometric task of 3D segmentation using 2D CNNs and the structured representation - concluding the utility of such descriptors for both discriminative and geometric tasks.