In short, Image analyse is a container for all the efforts that are not part any other theme. This is image segmentation and matting, that is the recovery of fine sub-pixel structures, such as hair. In this context we also look at the topic of image co-segmentation, the joint segmentation of an object in multiple images. We also do image de-convolution and de-noising, for which we have recently developed learning-based approaches. Finally, we are looking at intrinsic image de-composition that is the decomposition of a given image into a material image and an image that describes the lighting effects.
- Alpha Matting Benchmark page (project was run by Christoph Rhemann from TU Vienna)
- U. Schmidt, C. Rother, S. Nowozin, J. Jancsary, and S. Roth, Discriminative Non-blind Deblurring, CVPR 2013, Best student paper award
- P. Kohli, H. Nickisch, C. Rother, and C. Rhemann, User-centric Learning and Evaluation of Interactive Segmentation Systems , IJCV 2012.
- S. Vicente, C. Rother, and V. Kolmogorov, Object Cosegmentation, CVPR 2011.
- C. Rhemann, C. Rother, P. Kohli, and M. Gelautz, A Spatially Varying PSF-based Prior for Alpha Matting, CVPR 2010.
- A. Mansfield, P. Gehler, L. V. Gool, and C. Rother, Scene Carving: Scene Consistent Image Retargeting, ECCV 2010.
- C. Rhemann, C. Rother, J. Wang, M. Gelautz, P. Kohli, and P. Rott, A Perceptually Motivated Online Benchmark for Image Matting, CVPR, 2009
- C. Rother, V. Kolmogorov, T. Minka, and A. Blake, Cosegmenting Image Pairs by Matching Global Histograms, CVPR 2006.
- C. Rother, V. Kolmogorov, and A. Blake, GrabCut-Interactive Foreground Extraction using Iterated Graph Cuts, ACM Transactions onGraphics (SIGGRAPH), 2004.