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 = {Litman, R and Bronstein, AM and Bronstein, MM},
doi = {10.1016/j.cag.2012.03.034},
pages = {569--576},
title = {Stable volumetric features in deformable shapes},
url = {},
year = {2012}

RIS format (EndNote, RefMan)

AB - Region feature detectors and descriptors have become a successful and popular alternative to point descriptors in image analysis due to their high robustness and repeatability, leading to a significant interest in the shape analysis community in finding analogous approaches in the 3D world. Recent works have successfully extended the maximally stable extremal region (MSER) detection algorithm to surfaces. In many applications, however, a volumetric shape model is more appropriate, and modeling shape deformations as approximate isometries of the volume of an object, rather than its boundary, better captures natural behavior of non-rigid deformations. In this paper, we formulate a diffusion-geometric framework for volumetric stable component detection and description in deformable shapes. An evaluation of our method on the SHREC11 feature detection benchmark and SCAPE human body scans shows its potential as a source of high-quality features. Examples demonstrating the drawbacks of surface stable components and the advantage of their volumetric counterparts are also presented. © 2012 Elsevier Ltd. All rights reserved.
AU - Litman,R
AU - Bronstein,AM
AU - Bronstein,MM
DO - 10.1016/j.cag.2012.03.034
EP - 576
PY - 2012///
SN - 0097-8493
SP - 569
TI - Stable volumetric features in deformable shapes
UR -
ER -