Master2: Spacetime signatures of shapes in motion

We are looking for a highly motivated Master student to work on the subject of spacetime signatures of shapes in motion.


GPS signature of a mesh [Rus07] (image by Benjelloun, Lebas, Michaud 2012, model courtesy of Vlasic, Baran, Matusik and Popović )



Recent results obtained in computer vision with multiple camera systems allow to recover dense information on shapes and their motions. This ability to perceive shapes in motion brings a new and rich domain for research investigations on the analysis of moving objects, in particular human motions. In order to enable such analysis several challenges need to be faced. First, relevant indices that describe shapes and especially their dynamic evolutions must be found. Second, compact representations must be build for analysis purposes. The purpose of this work is to tackle both problems by defining a spacetime signature that encodes both shape and motion information.


Assume that a shape model and its motion over time are available. The objective is to define a signature that enables to discriminate this shape in motion from other shapes and motions. Ideally, this signature should enable the identification of both the shape and its motion. Several shape signatures have already been proposed for static shapes. In that case, signatures can be modeled as distributions [OFCD02], histograms [GSCO07,ZBVH09], matrices [Rus07], functions [SOG09], or even as a combination of subpart signatures [TCF09,BBGO11]. The objective of this project will be to consider their extensions to the dynamic case.

During the internship, the project tasks will be in order:

  1. Review existing works on static shape signatures.
  2. Design and implement an extension of one of them for shapes in motion.
  3. Thoroughly evaluate the performances of this signature with respect to: invariance to space scale and time scale, shape invariance, motion invariance, geometric or temporal noise, etc.
  4. Based on this signature, design an algorithm for shape and motion classification.

Computer vision, computer graphics, geometry processing, shape analysis, computer animation, feature descriptor.

Student profile

  • Master student, preferably in computer science or applied mathematics.
  • Creative and highly motivated.
  • Solid programming skills; the project involves programming in C++, Matlab.
  • Solid mathematics knowledge (especially linear algebra, numerical analysis and geometry).
  • Fluent English or French spoken, and fluent written English.
  • Prior knowledge in the areas of computer vision, computational geometry, computer graphics and/or signal processing is a plus.

Duration: 5 to 7 months.

Start date: February 2013.

Location: Inria Grenoble Rhône-Alpes, France.

How to apply

Please send applications through this page:

  • a complete CV
  • graduation marks, rankings
  • the name and email address of references, if relevant


Franck Hétroy, Morpheo team
Edmond Boyer, Morpheo Team
LJK & Inria
E-mail :
Tel.: 04 76 61 55 04
E-mail :
Tel.: 04 76 61 53 54


  • [BBGO11] A.M. Bronstein, M.M. Bronstein, L. Guibas and M. Ovsjanikov. Shape Google: Geometric Words and Expressions for Invariant Shape Retrieval. Transactions on Graphics 30(1), 2011.
  • [GSCO07] R. Gal, A. Shamir and D. Cohen-Or. Pose-Oblivious Shape Signature. Transactions on Visualization and Computer Graphics 13(2), 2007.
  • [OFCD02] R. Osada, T. Funkhouser, B. Chazelle and D. Dobkin. Shape Distributions. Transactions on Graphics 21(4), 2002.
  • [Rus07] R. Rustamov. Laplace-Beltrami Eigenfunctions for Deformation Invariant Shape Representation. Symposium on Geometry Processing, 2007.
  • [SOG09] J. Sun, M. Ovsjanikov and L. Guibas. A Concise and Provably Informative Multi-Scale Signature Based on Heat Diffusion. Symposium on Geometry Processing, 2009.
  • [TCF09] R. Toldo, U. Castellani and A. Fusiello. Visual Vocabulary Signature for 3D Object Retrieval and Partial Matching. Eurographics Workshop on 3D Object Retrieval, 2009.
  • [ZBVH09] A. Zaharescu, E. Boyer, K. Varanasi and R. Horaud. Surface Feature Detection and Description with Applications to Mesh Matching. Computer Vision and Pattern Recognition, 2009.