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.
@article{arxiv.2306.05246,
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},
journal= {arXiv preprint arXiv:2306.05246},
year = {2023}
}