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 = {Litany, O and Bronstein, A and Bronstein, M and Makadia, A},
doi = {10.1109/CVPR.2018.00202},
pages = {1886--1895},
title = {Deformable Shape Completion with Graph Convolutional Autoencoders},
url = {},
year = {2018}

RIS format (EndNote, RefMan)

AB - © 2018 IEEE. The availability of affordable and portable depth sensors has made scanning objects and people simpler than ever. However, dealing with occlusions and missing parts is still a significant challenge. The problem of reconstructing a (possibly non-rigidly moving) 3D object from a single or multiple partial scans has received increasing attention in recent years. In this work, we propose a novel learning-based method for the completion of partial shapes. Unlike the majority of existing approaches, our method focuses on objects that can undergo non-rigid deformations. The core of our method is a variational autoencoder with graph convolutional operations that learns a latent space for complete realistic shapes. At inference, we optimize to find the representation in this latent space that best fits the generated shape to the known partial input. The completed shape exhibits a realistic appearance on the unknown part. We show promising results towards the completion of synthetic and real scans of human body and face meshes exhibiting different styles of articulation and partiality.
AU - Litany,O
AU - Bronstein,A
AU - Bronstein,M
AU - Makadia,A
DO - 10.1109/CVPR.2018.00202
EP - 1895
PY - 2018///
SN - 1063-6919
SP - 1886
TI - Deformable Shape Completion with Graph Convolutional Autoencoders
UR -
ER -