<< homeResearch

Research overview by topic with selected publications.

3D Surface Reconstruction

Recovering dense 3D shapes and surfaces from image data using image observations of points, lines, contours and their visibility.

Solem, J.E. and Heyden, A., Reconstructing Open Surfaces from Image Data, International Journal of Computer Vision, volume 69, issue 3, September 2006.

Solem, J.E., Aanaes, H. and Heyden, A., Variational Surface Interpolation from Sparse Point and Normal Data, IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 29, no 1, January 2006.

Solem, J.E., Kahl, F. and Heyden, A., Visibility Constrained Surface Evolution, in Proc. International Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA, 2005.

Solem, J.E. and Heyden, A., Reconstructing Open Surfaces from Unorganized Data Points, in Proc. International Conference on Computer Vision and Pattern Recognition, Washington DC, USA, 2004. (Best Poster Award)

Variational Problems and Optimization

Mathematical framework for analyzing variational surface problems and methods for solving them.

Solem, J.E., Overgaard, N.C., Region-Based Variational Problems and Normal Alignment -- Geometric Interpretation of Descent PDEs, in Image Processing Based on Partial Differential Equations, Springer-Verlag, 2007.

Overgaard, N.C. and Solem, J.E., The Variational Origin of Motion by Gaussian Curvature, in Proc. First International Conference on Scale Space Methods and Variational Methods in Computer Vision (SSVM), Ischia, Italy, 2007.

Solem, J.E. and Overgaard, N.C., A Geometric Formulation of Gradient Descent for Variational Problems with Moving Surfaces, in Proc. 5th International Conference on Scale Space and PDE Methods in Computer Vision, Scale Space 2005, Hofgeismar, Germany, 2005.

Solem, J.E. and Overgaard, N.C., A Gradient Descent Procedure for Variational Dynamic Surface Problems with Constraints, in Proc. IEEE Workshop on Variational, Geometric and Level Set Methods in Computer Vision, Beijing, China, 2005.

Segmentation

Robust techniques for partitioning 2D or 3D images into consistent regions based on image data.

Solem, J.E., Overgaard, N.C. and Heyden, A., Initialization Techniques for Segmentation with the Chan-Vese Model, in Proc. International Conference on Pattern Recognition, Hong Kong, 2006.

Solem, J.E., Overgaard, N.C., Persson, M. and Heyden, A., Fast Variational Segmentation using Partial Extremal Initialization, in Proc. International Conference on Computer Vision and Pattern Recognition, New York, NY, USA, 2006.

Solem, J.E., Persson, M. and Heyden, A., Velocity Based Segmentation in Phase Contrast MRI Images, in Proc. Seventh International Conference on Medical Image Computing and Computer-Assisted Intervention, Rennes - Saint Malo, France, 2004.

Recognition

Recovering 3D shapes of objects using shape priors and localizing object landmarks using appearance models.

Netzell, K. and Solem, J.E., Efficient Image Inner Products Applied to Active Appearance Models, in Proc. International Conference on Pattern Recognition, 2008.

Solem, J.E. and Kahl, F., Surface Reconstruction Using Learned Shape Models, in Neural Information Processing Systems, Vancouver, Canada, 2004.

Shape analysis

Represent and recognize shapes without the need for parameterization or registration.

Solem, J.E., Geodesic Curves for Analysis of Continuous Implicit Shapes, in Proc. International Conference on Pattern Recognition, Hong Kong, 2006.

Overgaard, N.C. and Solem, J.E., Separating Rigid Motion for Continuous Shape Evolution, in Proc. International Conference on Pattern Recognition, Hong Kong, 2006.