Logo image
Back
HyNet: 3D Segmentation Using Hybrid Graph Networks
Conference proceeding

HyNet: 3D Segmentation Using Hybrid Graph Networks

Bahareh Shakibajahromi, Saeed Shayestehmanesh, Daniel Schwartz and Ali Shokoufandeh
2021 International Conference on 3D Vision (3DV), pp 805-814
Dec 2021
DOI: https://doi.org/10.1109/3DV53792.2021.00089

Abstract

Biological system modeling Deep learning Focusing Representation learning Shape Solid modeling Three-dimensional displays
Mesh is a preeminent and efficient data structure for 3D objects that support high-resolution representation. Recent deep learning techniques applied to unstructured mesh data define rigid convolutions that fail to capture the rich geometric and topological attributes of the mesh. We propose an efficient, deterministic process that converts a mesh into a hybrid graph and captures the geometric features of its constituting components: vertices, edges, and faces. In addition, we introduce a novel representation learning framework that encodes mesh elements by focusing on the most relevant parts of the geometric structure using a dual-level attention architecture. We evaluate the efficacy of the proposed representation in the context of the 3D shape segmentation problem. The superior performance of the proposed representation to the state of the art in supervised segmentation illustrates the soundness of the proposed attention model.

Metrics

10 Record Views
1 citations in Web of Science
2 citations in Scopus

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Domestic collaboration
Web of Science research areas
Computer Science, Artificial Intelligence
Computer Science, Software Engineering
Engineering, Electrical & Electronic
Imaging Science & Photographic Technology
Logo image