A Geometric Approach to Image Labeling
- 6.6k Downloads
We introduce a smooth non-convex approach in a novel geometric framework which complements established convex and non-convex approaches to image labeling. The major underlying concept is a smooth manifold of probabilistic assignments of a prespecified set of prior data (the “labels”) to given image data. The Riemannian gradient flow with respect to a corresponding objective function evolves on the manifold and terminates, for any \(\delta > 0\), within a \(\delta \)-neighborhood of an unique assignment (labeling). As a consequence, unlike with convex outer relaxation approaches to (non-submodular) image labeling problems, no post-processing step is needed for the rounding of fractional solutions. Our approach is numerically implemented with sparse, highly-parallel interior-point updates that efficiently converge, largely independent from the number of labels. Experiments with noisy labeling and inpainting problems demonstrate competitive performance.
KeywordsImage labeling Assignment manifold Fisher-Rao metric Riemannian gradient flow
FÅ, SP and CS thank the German Research Foundation (DFG) for support via grant GRK 1653. BS was supported by the European Research Council (project SIGMA-Vision).
- 2.Kappes, J., Andres, B., Hamprecht, F., Schnörr, C., Nowozin, S., Batra, D., Kim, S., Kausler, B., Kröger, T., Lellmann, J., Komodakis, N., Savchynskyy, B., Rother, C.: A comparative study of modern inference techniques for structured discrete energy minimization problems. Int. J. Comp. Vis. 115(2), 155–184 (2015)MathSciNetCrossRefGoogle Scholar
- 5.Sundaramoorthi, G., Hong, B.W.: Fast label: easy and efficient solution of joint multi-label and estimation problems. In: 2014 CVPR, pp. 3126–3133, June 2014Google Scholar
- 6.Jung, M., Chung, G., Sundaramoorthi, G., Vese, L.A., Yuille, A.L.: Sobolev gradients and joint variational image segmentation, denoising, and deblurring. In: Proceedings of the SPIE, vol. 7246, pp. 72460I–72460I-13 (2009)Google Scholar
- 7.Åström, F., Petra, S., Schmitzer, B., Schnörr, C.: Image Labeling by Assignment 16 March 2016, preprint: http://arxiv.org/abs/1603.05285
- 8.Amari, S.I., Nagaoka, H.: Methods of Information Geometry. Amer. Math. Soc. and Oxford University Press (2000)Google Scholar
- 12.C̆encov, N.: Statistical Decision Rules and Optimal Inference. Amer. Math. Soc. (1982)Google Scholar
- 16.Andres, B., Beier, T., Kappes, J.: OpenGM: A C++ library for discrete graphical models. CoRR abs/1206.0111 (2012)Google Scholar