A Task-driven Network for Mesh Classification and Semantic Part Segmentation

Qiujie Dong, Xiaoran Gong, Rui Xu, Zixiong Wang, Shuangmin Chen +3 more
6/8/2023
cs.CVcs.GR

No official code found. Best implementation: QiujieDong/TaskDrivenNet2Mesh (9 stars, MIT, last commit 2024-05-27).

Abstract

With the rapid development of geometric deep learning techniques, many mesh-based convolutional operators have been proposed to bridge irregular mesh structures and popular backbone networks. In this paper, we show that while convolutions are helpful, a simple architecture based exclusively on multi-layer perceptrons (MLPs) is competent enough to deal with mesh classification and semantic segmentation. Our new network architecture, named Mesh-MLP, takes mesh vertices equipped with the heat kernel signature (HKS) and dihedral angles as the input, replaces the convolution module of a ResNet with Multi-layer Perceptron (MLP), and utilizes layer normalization (LN) to perform the normalization of the layers. The all-MLP architecture operates in an end-to-end fashion and does not include a pooling module. Extensive experimental results on the mesh classification/segmentation tasks validate the effectiveness of the all-MLP architecture.

View on arXivView PDF

Code Implementations(1)

QiujieDong/TaskDrivenNet2MeshCommunity68%
MIT

A Task-driven Network for Mesh Classification and Semantic Part Segmentation

93Shell, PythonApr 20, 20242 years agoMIT

Similar Papers

InfoGNN: End-to-end deep learning on mesh via graph neural networks

83% match2025

Depth-aware CNN for RGB-D Segmentation

82% match1 repo3062018

Joint Neural SDF Reconstruction and Semantic Segmentation for CAD Models

82% match2025

MeshConv3D: Efficient convolution and pooling operators for triangular 3D meshes

82% match2025

HodgeFormer: Transformers for Learnable Operators on Triangular Meshes through Data-Driven Hodge Matrices

82% match2025

SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels

82% match1 repo24.1k2017

Cite this paper

@article{dong2023taskdriven,
  title  = {A Task-driven Network for Mesh Classification and Semantic Part Segmentation},
  author = {Qiujie Dong and Xiaoran Gong and Rui Xu and Zixiong Wang and Shuangmin Chen and Shiqing Xin and Changhe Tu and Wenping Wang},
  year   = {2023},
  eprint = {2306.05246},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.05246v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.05246.svg)](https://codeofpaper.com/paper/2306.05246)

Discussion