Home Call for papers People Dates Program Submission CVPR'11











9:00 - 10:00 Keynote talk "From Eye-Balls to Ball-Games: Recent trends in non-rigid capture and reconstruction", Christoph Bregler (Courant Institute, New York University)

This talk focuses on the trade-off between low-dimensional factorial models (NRSfM) that can extract non-rigid models from a very small amount of data versus very data-intensive crowd-sourced techniques that result in deep, high-dimensional representations. This is demonstrated on sub-pixel tracking in Hollywood productions, reading the body-language of public figures, visualizing the pitches of NY Yankee Mariano Rivera, and deriving pose spaces from conference speakers as well as fans from a Dutch progressive-electro band.


10:00 - 10:30 Coffee break


Morning session
  • 10:30 - 11:00 Dense Shape Correspondences using Spectral High-Order Graph Matching, Dirk Smeets, Jeroen Hermans, Dirk Vandermeulen, Paul Suetens
  • 11:00 - 11:30 Temperature Distribution Descriptor for Robust 3D Shape Retrieval, Yi Fang, Mengtian Sun, Karthik Ramani
  • 11:30 - 12:00 Efficient Nonlinear DTI Registration Using DCT Basis Functions, Lin Gan, Gady Agam

13:30 - 14:30 Keynote talk "4D Performance Modelling and Animation", Adrian Hilton (University of Surrey)

Visual reconstruction of dynamic events as 3D video, such as an actor performance or sports action, has advanced to the stage where it is possible to achieve free-viewpoint replay with a quality approaching the captured video. In this talk we present research going beyond replay to allow the creation of 4D models which support interactive animation control from captured performance whilst maintaining the realism of video. 4D models are constructed by alignment of reconstructed mesh sequences into a temporally coherent structure. Recent work has introduced a non-sequential approach to non-rigid mesh mesh sequence alignment which constructs a shape similarity tree to align across a database of multiple sequences. This avoids problems of drift and tracking failure associated with sequential alignment approaches. Temporally aligned 4D models provide the basis for parameterisation of multiple related sequences to give continuous interactive movement control. Representation of multiple sequences in a 4D parametric motion graph enables transition between multiple motions to achieve interactive character animation.


Afternoon session
  • 14:30 - 15:00 Consistent Pose Normalization of Non-Rigid Shapes using One-Class Support Vector Machines, Panagiotis Papadakis, Fiora Pirri
  • 15:00 - 15:30 Resolving Occlusion in Multiframe Reconstruction of Deformable Surfaces, Appu Shaji, Aydin Varol, Pascal Fua, Yashoteja Ankush, Jain Sharat, Chandran

15:30 - 16:00 Coffee break


16:00 - 17:00 Keynote talk "Dense Non-rigid Surface Registration Using High-Order Graph Matching and Quasi-Conformal Geometry"Dimitris Samaras (University of Stony Brook)

I will present our most recent techniques for non-rigid surface matching and tracking combining quasi-conformal mappings with efficient global optimization methods. I will first describe a high-order graph matching formulation to address non-rigid surface matching. The singleton terms capture the geometric and appearance similarities (e.g., curvature and texture) while the high-order terms model the intrinsic embedding energy. The method includes: 1) casting 3D surface registration into a graph matching problem that combines both geometric and appearance similarities and intrinsic embedding information, 2) the first implementation of high-order graph matching algorithm that solves a non-convex optimization problem, and 3) an efficient two-stage optimization approach to constrain the search space for dense surface registration. Furthermore by considering the set of all possible 3D surface matchings defined by specifying triplets of correspondences in the uniformization domain, we introduce a new matching cost between two 3D surfaces, which can be efficiently computed for surface tracking applications. Our method is validated through a series of experiments demonstrating its accuracy and efficiency, notably in challenging cases of large and/or non-isometric deformations, or meshes that are partially occluded, as well as dense, anisometric 3D surface tracking experiments.


Afternoon session II
  • 17:00 - 17:30 Separating Rigid Motion from Local Linear Deformation Models, Markus Moll, Luc Van Gool
  • 17:30 - 18:00 Deformable Image Alignment as a Source of Stereo Correspondences on Portraits, David C. Schneider, Markus Kettern, Anna Hilsmann, Peter Eisert