Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Mesh variational autoencoders with edge contraction pooling

Yuan, Yu-Jie, Lai, Yu-kun ORCID: https://orcid.org/0000-0002-2094-5680, Yang, Jie, Duan, Qi, Fu, Hongbo and Gao, Lin 2020. Mesh variational autoencoders with edge contraction pooling. Presented at: CVPR Workshop on Learning 3D Generative Models, Seattle, WA, USA, 14 June 2020.

[thumbnail of MeshPoolingCVPRW20.pdf]
Preview
PDF - Accepted Post-Print Version
Download (1MB) | Preview

Abstract

3D shape analysis is an important research topic in computer vision and graphics. While existing methods have generalized image-based deep learning to meshes using graph-based convolutions, the lack of an effective pooling operation restricts the learning capability of their networks. In this paper, we propose a novel pooling operation for mesh datasets with the same connectivity but different geometry,by building a mesh hierarchy using mesh simplification. For this purpose, we develop a modified mesh simplification method to avoid generating highly irregularly sized triangles. Our pooling operation effectively encodes the correspondence between coarser and finer meshes in the hierarchy. We then present a variational auto-encoder (VAE) structure with the edge contraction pooling and graphbased convolutions, to explore probability latent spaces of 3D surfaces and perform 3D shape generation. Our network requires far fewer parameters than the original mesh VAE and thus can handle denser models thanks to our new pooling operation and convolutional kernels. Our evaluation also shows that our method has better generalization ability and is more reliable in various applications, including shape generation and shape interpolation.

Item Type: Conference or Workshop Item (Paper)
Status: In Press
Schools: Computer Science & Informatics
Funders: The Royal Society
Date of First Compliant Deposit: 23 April 2020
Date of Acceptance: 19 April 2020
Last Modified: 07 Nov 2022 10:07
URI: https://orca.cardiff.ac.uk/id/eprint/131187

Citation Data

Cited 17 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics