# 3D Mesh Segmentation via Multi-branch 1D Convolutional Neural Networks

## TL;DR

This paper introduces a novel multi-branch 1D CNN for 3D mesh segmentation, addressing issues of speed, sensitivity, and reproducibility in existing methods, and provides comprehensive baseline comparisons.

## Contribution

It proposes a new CNN architecture with a robust conformal factor computation and offers a comparative study of deep learning techniques for mesh segmentation.

## Key findings

- Our method outperforms existing techniques in accuracy.
- The new conformal factor computation enhances segmentation robustness.
- Comprehensive benchmarks of deep learning models are provided.

## Abstract

There is an increasing interest in applying deep learning to 3D mesh segmentation. We observe that 1) existing feature-based techniques are often slow or sensitive to feature resizing, 2) there are minimal comparative studies and 3) techniques often suffer from reproducibility issue. This study contributes in two ways. First, we propose a novel convolutional neural network (CNN) for mesh segmentation. It uses 1D data, filters and a multi-branch architecture for separate training of multi-scale features. Together with a novel way of computing conformal factor (CF), our technique clearly out-performs existing work. Secondly, we publicly provide implementations of several deep learning techniques, namely, neural networks (NNs), autoencoders (AEs) and CNNs, whose architectures are at least two layers deep. The significance of this study is that it proposes a robust form of CF, offers a novel and accurate CNN technique, and a comprehensive study of several deep learning techniques for baseline comparison.