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

Source: [A Task-driven Network for Mesh Classification and Semantic Part Segmentation](<https://www.sota2.com/research/paper/68fa719f1e209131cea52238>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:28:17.503Z

Authors: Qiujie Dong, Xiaoran Gong, Rui Xu, Zixiong Wang, Shuangmin Chen, Shiqing Xin, Changhe Tu, Wenping Wang

Published: 2023-06-08T14:44:57.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.05246>)

[PDF](<https://arxiv.org/pdf/2306.05246.pdf>)