Aug 23, 2019 · 3DTI-Net consists of a transform invariant feature encoder as the front-end and a hierarchical graph convolutional neural network as the back- ...
3DTI-Net consists of a transform invariant feature encoder as the front-end and a hierarchical graph convolutional neural network as the back-end. It achieves ...
3DTI-Net is able to learn 3D feature efficiently and can achieve state-of-the-art performance in rotated 3D object classification and retrieval.
3DTI-Net: Learn 3D Transform-Invariant Feature Using Hierarchical Graph CNN. Work. HTML. Year: 2019. Type: book-chapter. Source: Lecture notes in computer ...
3DTI-Net consists of a transform invariant feature encoder as the front-end and a hierarchical graph convolutional neural network as the back-end. It achieves ...
This paper proposes a general framework for point cloud learning, achieves transform invariance by learning inner 3D geometry feature based on local graph ...
Dec 15, 2018 · In this paper, we propose a general framework for point cloud learning. We achieve transform invariance by learning inner 3D geometry feature based on local ...
Missing: Hierarchical CNN.
In this paper, we propose a general framework for point cloud learning. We achieve transform invariance by learning inner 3D geometry feature based on local ...
Apr 25, 2024 · Guanghua Pan, Peilin Liu, Jun Wang, Rendong Ying, Fei Wen: 3DTI-Net: Learn 3D Transform-Invariant Feature Using Hierarchical Graph CNN.
刘佩林,Liu Peilin,上海交大研究生院主页平台管理系统, 3DTI-Net: Learn 3D Transform-invariant Feature Using Hierarchical Graph CNN 人工智能，机器视觉， 3D视觉， ...