Abstract
We propose an adaptive regularization scheme in a variational framework where a convex composite energy functional is optimized. We consider a number of imaging problems including segmentation and motion estimation, which are considered as optimal solutions of the energy functionals that mainly consist of data fidelity, regularization and a control parameter for their trade-off. We presents an algorithm to determine the relative weight between data fidelity and regularization based on the residual that measures how well the observation fits the model. Our adaptive regularization scheme is designed to locally control the regularization at each pixel based on the assumption that the diversity of the residual of a given imaging model spatially varies. The energy optimization is presented in the alternating direction method of multipliers (ADMM) framework where the adaptive regularization is iteratively applied along with mathematical analysis of the proposed algorithm. We demonstrate the robustness and effectiveness of our adaptive regularization through experimental results presenting that the qualitative and quantitative evaluation results of each imaging task are superior to the results with a constant regularization scheme. The desired properties, robustness and effectiveness, of the regularization parameter selection in a variational framework for imaging problems are achieved by merely replacing the static regularization parameter with our adaptive one.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The ground truth boundary is not uniquely provided in the Berkeley dataset and we have chosen the one suited for our bi-partitioning segmentation model.
References
Ayvaci, A., Raptis, M., Soatto, S.: Occlusion detection and motion estimation with convex optimization. In: Advances in Neural Information Processing Systems, pp. 100–108 (2010)
Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. Int. J. Comput. Vis. 92(1), 1–31 (2011)
Barron, J.L., Fleet, D.J., Beauchemin, S.S.: Performance of optical flow techniques. Int. J. Comput. Vis. 12(1), 43–77 (1994)
Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2(1), 183–202 (2009)
Becker, S., Bobin, J., Candès, E.J.: Nesta: a fast and accurate first-order method for sparse recovery. SIAM J. Imaging Sci. 4(1), 1–39 (2011)
Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn. 3(1), 1–122 (2010)
Bresson, X., Esedo\(\bar{\rm g}\)lu, S., Vandergheynst, P., Thiran, J.P., Osher, S.: Fast global minimization of the active contour/snake model. J. Math. Imaging Vis. 28(2), 151–167 (2007)
Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. Int. J. Comput. Vis. 22(1), 61–79 (1997)
Chambolle, A., Cremers, D., Pock, T.: A convex approach to minimal partitions. SIAM J. Imaging Sci. 5(4), 1113–1158 (2012)
Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vis. 40(1), 120–145 (2011)
Chan, T.F., Esedoglu, S., Nikolova, M.: Algorithms for finding global minimizers of image segmentation and denoising models. SIAM J. Appl. Math. 66(5), 1632–1648 (2006)
Chan, T.F., Vese, L.A.: Active contours without edges. IEEE Trans. Image Process. 10(2), 266–277 (2001)
Chantas, G., Gkamas, T., Nikou, C.: Variational-Bayes optical flow. J. Math. Imaging Vis. 50(3), 199–213 (2014)
Galatsanos, N.P., Katsaggelos, A.K.: Methods for choosing the regularization parameter and estimating the noise variance in image restoration and their relation. IEEE Trans. Image Process. 1(3), 322–336 (1992)
Hintermüller, M., Wu, T.: Nonconvex tv \(\hat{}\)q-models in image restoration: analysis and a trust-region regularization-based superlinearly convergent solver. SIAM J. Imaging Sci. 6(3), 1385–1415 (2013)
Horn, B.K., Schunck, B.G.: Determining optical flow. In: 1981 Technical Symposium East, pp. 319–331. International Society for Optics and Photonics (1981)
Krähenbühl, P., Koltun, V.: Efficient nonlocal regularization for optical flow. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 356–369. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33718-5_26
Krajsek, K., Mester, R.: A maximum likelihood estimator for choosing the regularization parameters in global optical flow methods. In: 2006 IEEE International Conference on Image Processing, pp. 1081–1084. IEEE (2006)
Lee, K.J., Kwon, D., Yun, D., Lee, S.U., et al.: Optical flow estimation with adaptive convolution kernel prior on discrete framework. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2504–2511. IEEE (2010)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings of the 8th International Conference on Computer Vision, vol. 2, pp. 416–423, July 2001
Möllenhoff, T., Strekalovskiy, E., Moeller, M., Cremers, D.: The primal-dual hybrid gradient method for semiconvex splittings. SIAM J. Imaging Sci. 8(2), 827–857 (2015)
Nesterov, Y., Nemirovskii, A., Ye, Y.: Interior-Point Polynomial Algorithms in Convex Programming, vol. 13. SIAM, Philadelphia (1994)
Ng, L., Solo, V.: A data-driven method for choosing smoothing parameters in optical flow problems. In: Proceedings of the International Conference on Image Processing, 1997, vol. 3, pp. 360–363. IEEE (1997)
Nguyen, N., Milanfar, P., Golub, G.: Efficient generalized cross-validation with applications to parametric image restoration and resolution enhancement. IEEE Trans. Image Process. 10(9), 1299–1308 (2001)
Nikolova, M., Ng, M.K., Tam, C.P.: Fast nonconvex nonsmooth minimization methods for image restoration and reconstruction. IEEE Trans. Image Process. 19(12), 3073–3088 (2010)
Ochs, P., Dosovitskiy, A., Brox, T., Pock, T.: An iterated L1 algorithm for non-smooth non-convex optimization in computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1759–1766 (2013)
Otte, M., Nagel, H.-H.: Optical flow estimation: advances and comparisons. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 800, pp. 49–60. Springer, Heidelberg (1994). doi:10.1007/3-540-57956-7_5
Peng, B., Veksler, O.: Parameter selection for graph cut based image segmentation. In: BMVC, vol. 32, pp. 42–44 (2008)
Pérez, J.S., Meinhardt-Llopis, E., Facciolo, G.: TV-L1 optical flow estimation. Image Process. On Line 2013, 137–150 (2013)
Pock, T., Chambolle, A.: Diagonal preconditioning for first order primal-dual algorithms in convex optimization. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 1762–1769. IEEE (2011)
Ranftl, R., Bredies, K., Pock, T.: Non-local total generalized variation for optical flow estimation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 439–454. Springer, Cham (2014). doi:10.1007/978-3-319-10590-1_29
Thompson, A.M., Brown, J.C., Kay, J.W., Titterington, D.M.: A study of methods of choosing the smoothing parameter in image restoration by regularization. IEEE Trans. Pattern Anal. Mach. Intell. 4, 326–339 (1991)
Unger, M., Werlberger, M., Pock, T., Bischof, H.: Joint motion estimation and segmentation of complex scenes with label costs and occlusion modeling. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1878–1885. IEEE (2012)
Wedel, A., Cremers, D., Pock, T., Bischof, H.: Structure-and motion-adaptive regularization for high accuracy optic flow. In: ICCV, pp. 1663–1668 (2009)
Wedel, A., Pock, T., Zach, C., Bischof, H., Cremers, D.: An improved algorithm for TV-\(L^1\) optical flow. In: Cremers, D., Rosenhahn, B., Yuille, A.L., Schmidt, F.R. (eds.) Statistical and Geometrical Approaches to Visual Motion Analysis. LNCS, vol. 5604, pp. 23–45. Springer, Heidelberg (2009). doi:10.1007/978-3-642-03061-1_2
Werlberger, M., Pock, T., Bischof, H.: Motion estimation with non-local total variation regularization. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2464–2471. IEEE (2010)
Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., Bischof, H.: Anisotropic Huber-l1 optical flow. In: BMVC. vol. 1, p. 3 (2009)
Acknowledgement
This work was supported by NRF-2014R1A2A1A11051941 and NRF-2017R1A2B4006023.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Hong, BW., Koo, JK., Dirks, H., Burger, M. (2017). Adaptive Regularization in Convex Composite Optimization for Variational Imaging Problems. In: Roth, V., Vetter, T. (eds) Pattern Recognition. GCPR 2017. Lecture Notes in Computer Science(), vol 10496. Springer, Cham. https://doi.org/10.1007/978-3-319-66709-6_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-66709-6_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-66708-9
Online ISBN: 978-3-319-66709-6
eBook Packages: Computer ScienceComputer Science (R0)