Persönlicher Status und Werkzeuge

Home Research Shape Priors

Shape Priors

In this project, we introduce into classical image segmentation methods some prior knowledge about which shapes are likely to be in a given image. In particular, we develop metrics on spaces of shapes, statistical models of shape variation and dynamical models which allow to impose a statistical model of the temporal evolution of shape. The respective segmentation processes can cope with large amounts of background clutter, noise and partial or complete occlusions.

Click on the images to view animations.

IJCV '02 (movie) ECCV '02 (movie) PAMI '06 (movie)

Related publications

Book Chapters
2007
Efficient kernel density estimation of shape and intensity priors for level set segmentation (D. Cremers, M. Rousson), Chapter in Parametric and Geometric Deformable Models: An application in Biomaterials and Medical Imagery (J. S. Suri, A. Farag, eds.), Springer, 2007. [bib] [pdf]
Journal Articles
2009
Combined region- and motion-based 3D tracking of rigid and articulated objects (T. Brox, B. Rosenhahn, J. Gall, D. Cremers), In IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 32, 2009. [bib] [pdf]
2008
Nonlinear Dynamical Shape Priors for Level Set Segmentation (D. Cremers), In Journal of Scientific Computing, volume 35, 2008. [bib] [pdf]
2007
A review of statistical approaches to level set segmentation: integrating color, texture, motion and shape (D. Cremers, M. Rousson, R. Deriche), In International Journal of Computer Vision, volume 72, 2007. [bib] [pdf]
2006
Dynamical statistical shape priors for level set based tracking (D. Cremers), In IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 28, 2006. [bib] [pdf]
2003
Shape Statistics in Kernel Space for Variational Image Segmentation (D. Cremers, T. Kohlberger, C. Schnörr), In Pattern Recognition, volume 36, 2003. [bib] [pdf]Awarded Best Paper of the Year 2003
2002
Diffusion Snakes: Introducing statistical shape knowledge into the Mumford--Shah functional (D. Cremers, F. Tischhäuser, J. Weickert, C. Schnörr), In International Journal of Computer Vision, volume 50, 2002. [bib] [pdf]
Conference and Workshop Papers
2015
A Fast Projection Method for Connectivity Constraints in Image Segmentation (J. Stühmer, D. Cremers), In Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR) (X.-C. Tai, E. Bae, T. F. Chan, M. Lysaker, eds.), 2015. [bib] [pdf]
2013
Tree Shape Priors with Connectivity Constraints using Convex Relaxation on General Graphs (J. Stühmer, P. Schröder, D. Cremers), In IEEE International Conference on Computer Vision (ICCV), 2013. [bib] [pdf]Oral Presentation
2009
A Closed-Form Solution for Image Sequence Segmentation with Dynamical Shape Priors (F. R. Schmidt, D. Cremers), In Pattern Recognition (Proc. DAGM), 2009. [bib] [pdf]
2007
Nonlinear Dynamical Shape Priors for Level Set Segmentation (D. Cremers), In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2007. [bib] [pdf]
Globally Optimal Image Segmentation with an Elastic Shape Prior (T. Schoenemann, D. Cremers), In IEEE International Conference on Computer Vision (ICCV), 2007. [bib] [pdf]
2004
Multiphase dynamic labeling for variational recognition-driven image segmentation (D. Cremers, N. Sochen, C. Schnörr), In European Conference on Computer Vision (ECCV) (T. Pajdla, V. Hlavac, eds.), Springer, volume 3024, 2004. [bib] [pdf]
Kernel density estimation and intrinsic alignment for knowledge-driven segmentation: Teaching level sets to walk (D. Cremers, S. J. Osher, S. Soatto), In Pattern Recognition (Proc. DAGM) (C. E. Rasmussen, ed.), Springer, volume 3175, 2004. [bib] [pdf]
High accuracy optical flow estimation based on a theory for warping (T. Brox, A. Bruhn, N. Papenberg, J. Weickert), In European Conference on Computer Vision (ECCV) (T. Pajdla, J. Matas, eds.), Springer, volume 3024, 2004. [bib] [pdf]Received "The Longuet-Higgins Best Paper Award"
2003
Towards Recognition-based Variational Segmentation Using Shape Priors and Dynamic Labeling (D. Cremers, N. Sochen, C. Schnörr), In Scale-Space Methods in Computer Vision (L. D. Griffin, M. Lillholm, eds.), Springer, volume 2695, 2003. [bib] [pdf]
A pseudo-distance for shape priors in level set segmentation (D. Cremers, S. Soatto), In IEEE 2nd Int. Workshop on Variational, Geometric and Level Set Methods (N. Paragios, ed.), 2003. [bib] [pdf]
2002
Nonlinear shape statistics in Mumford--Shah based segmentation (D. Cremers, T. Kohlberger, C. Schnörr), In European Conference on Computer Vision (ECCV) (A. Heyden, others, eds.), Springer, volume 2351, 2002. [bib] [pdf]
2000
Diffusion Snakes using statistical shape knowledge (D. Cremers, C. Schnörr, J. Weickert, C. Schellewald), In Algebraic Frames for the Perception-Action Cycle (C. Sommer, Y.Y. Zeevi, eds.), Springer, volume 1888, 2000. [bib]
Learning of translation invariant shape knowledge for steering diffusion snakes (D. Cremers, C. Schnörr, J. Weickert, C. Schellewald), In Dynamische Perzeption (G. Baratoff, H. Neumann, eds.), Infix, volume 9, 2000. [bib]
Powered by bibtexbrowser
Export as PDF or BIB