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 = {Cosmo, L and Rodola, E and Masci, J and Torsello, A and Bronstein, MM},
doi = {10.1109/3DV.2016.10},
pages = {1--10},
title = {Matching deformable objects in clutter},
url = {},
year = {2016}

RIS format (EndNote, RefMan)

AB - © 2016 IEEE. We consider the problem of deformable object detection and dense correspondence in cluttered 3D scenes. Key ingredient to our method is the choice of representation: we formulate the problem in the spectral domain using the functional maps framework, where we seek for the most regular nearly-isometric parts in the model and the scene that minimize correspondence error. The problem is initialized by solving a sparse relaxation of a quadratic assignment problem on features obtained via data-driven metric learning. The resulting matching pipeline is solved efficiently, and yields accurate results in challenging settings that were previously left unexplored in the literature.
AU - Cosmo,L
AU - Rodola,E
AU - Masci,J
AU - Torsello,A
AU - Bronstein,MM
DO - 10.1109/3DV.2016.10
EP - 10
PY - 2016///
SP - 1
TI - Matching deformable objects in clutter
UR -
ER -