A task-driven network for mesh classification and semantic part segmentation

Qiujie Dong, Xiaoran Gong, Rui Xu, Zixiong Wang, Junjie Gao, Shuang-Min Chen, Shiqing Xin, Changhe Tu, Wenping Wang

Abstract: Highlights•A task-driven neural network that accommodates diverse mesh triangulations/resolutions and manifold/non-manifold mesh models.•Our method demonstrates robust learning capabilities for mesh classification and semantic segmentation tasks.•Extensive experiments were conducted, and all the results consistently validate the efficacy of our proposed approach.