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 Remez, T and Rodola, E and Bronstein, A and Bronstein, M},
doi = {10.1109/ICCV.2017.603},
pages = {5660--5668},
title = {Deep Functional Maps: Structured Prediction for Dense Shape Correspondence},
url = {},
year = {2017}

RIS format (EndNote, RefMan)

AB - © 2017 IEEE. We introduce a new framework for learning dense correspondence between deformable 3D shapes. Existing learning based approaches model shape correspondence as a labelling problem, where each point of a query shape receives a label identifying a point on some reference domain; the correspondence is then constructed a posteriori by composing the label predictions of two input shapes. We propose a paradigm shift and design a structured prediction model in the space of functional maps, linear operators that provide a compact representation of the correspondence. We model the learning process via a deep residual network which takes dense descriptor fields defined on two shapes as input, and outputs a soft map between the two given objects. The resulting correspondence is shown to be accurate on several challenging benchmarks comprising multiple categories, synthetic models, real scans with acquisition artifacts, topological noise, and partiality.
AU - Litany,O
AU - Remez,T
AU - Rodola,E
AU - Bronstein,A
AU - Bronstein,M
DO - 10.1109/ICCV.2017.603
EP - 5668
PY - 2017///
SN - 1550-5499
SP - 5660
TI - Deep Functional Maps: Structured Prediction for Dense Shape Correspondence
UR -
ER -