Neural 3D morphable models: Spiral convolutional networks for 3D shape representation learning and generation

Giorgos Bouritsas, Sergiy Bokhnyak, Stylianos Ploumpis, Stefanos Zafeiriou, Michael Bronstein

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Generative models for 3D geometric data arise in many important applications in 3D computer vision and graphics. In this paper, we focus on 3D deformable shapes that share a common topological structure, such as human faces and bodies. Morphable Models and their variants, despite their linear formulation, have been widely used for shape representation, while most of the recently proposed nonlinear approaches resort to intermediate representations, such as 3D voxel grids or 2D views. In this work, we introduce a novel graph convolutional operator, acting directly on the 3D mesh, that explicitly models the inductive bias of the fixed underlying graph. This is achieved by enforcing consistent local orderings of the vertices of the graph, through the spiral operator, thus breaking the permutation invariance property that is adopted by all the prior work on Graph Neural Networks. Our operator comes by construction with desirable properties (anisotropic, topology-aware, lightweight, easy-to-optimise), and by using it as a building block for traditional deep generative architectures, we demonstrate state-of-the-art results on a variety of 3D shape datasets compared to the linear Morphable Model and other graph convolutional operators.

Original languageEnglish
Title of host publicationProceedings - 2019 International Conference on Computer Vision, ICCV 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages7212-7221
Number of pages10
ISBN (Electronic)9781728148038
DOIs
StatePublished - Oct 2019
Externally publishedYes
Event17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 - Seoul, Korea, Republic of
Duration: 27 Oct 20192 Nov 2019

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2019-October
ISSN (Print)1550-5499

Conference

Conference17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
Country/TerritoryKorea, Republic of
CitySeoul
Period27/10/192/11/19

Funding

FundersFunder number
Department of Computing
Google
Engineering and Physical Sciences Research CouncilEP/S010203/1
Royal Society
Imperial College London
European Research Council724228

    Fingerprint

    Dive into the research topics of 'Neural 3D morphable models: Spiral convolutional networks for 3D shape representation learning and generation'. Together they form a unique fingerprint.

    Cite this