Imperial College London


Faculty of EngineeringDepartment of Computing

Chair in Machine Learning and Pattern Recognition



m.bronstein Website




569Huxley BuildingSouth Kensington Campus






BibTex format

author = {Bouritsas, G and Bokhnyak, S and Ploumpis, S and Bronstein, M and Zafeiriou, S},
title = {Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation},
url = {},

RIS format (EndNote, RefMan)

AB - Generative models for 3D geometric data arise in many important applicationsin 3D computer vision and graphics. In this paper, we focus on 3D deformableshapes that share a common topological structure, such as human faces andbodies. Morphable Models and their variants, despite their linear formulation,have been widely used for shape representation, while most of the recentlyproposed nonlinear approaches resort to intermediate representations, such as3D voxel grids or 2D views. In this work, we introduce a novel graphconvolutional operator, acting directly on the 3D mesh, that explicitly modelsthe inductive bias of the fixed underlying graph. This is achieved by enforcingconsistent local orderings of the vertices of the graph, through the spiraloperator, thus breaking the permutation invariance property that is adopted byall the prior work on Graph Neural Networks. Our operator comes by constructionwith desirable properties (anisotropic, topology-aware, lightweight,easy-to-optimise), and by using it as a building block for traditional deepgenerative architectures, we demonstrate state-of-the-art results on a varietyof 3D shape datasets compared to the linear Morphable Model and other graphconvolutional operators.
AU - Bouritsas,G
AU - Bokhnyak,S
AU - Ploumpis,S
AU - Bronstein,M
AU - Zafeiriou,S
TI - Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation
UR -
ER -