Abstract
We propose a variational aggregation method for optical flow estimation. It consists of a two-step framework, first estimating a collection of parametric motion models to generate motion candidates, and then reconstructing a global dense motion field. The aggregation step is designed as a motion reconstruction problem from spatially varying sets of motion candidates given by parametric motion models. Our method is designed to capture large displacements in a variational framework without requiring any coarse-to-fine strategy. We handle occlusion with a motion inpainting approach in the candidates computation step. By performing parametric motion estimation, we combine the robustness to noise of local parametric methods with the accuracy yielded by global regularization. We demonstrate the performance of our aggregation approach by comparing it to standard variational methods and a discrete aggregation approach on the Middlebury and MPI Sintel datasets.
Similar content being viewed by others
Notes
Without loss of generality, isotropic circular patches could be considered as well.
References
Alba, A., Arce-Santana, E., Riviera, M.: Optical flow estimation with prior models obtained from phase correlation. In: Advances in Visual Computing, pp. 417–426. Springer, Berlin (2010)
Arias, P., Facciolo, G., Caselles, V., Sapiro, G.: A variational framework for exemplar-based image inpainting. Int. J. Comput. Vis. 93(3), 319–347 (2011)
Ayvaci, A., Raptis, M., Soatto, S.: Sparse occlusion detection with optical flow. Int. J. Comput. Vis. 97(3), 322–338 (2012)
Bailer, C., Taetz, B., Stricker, D.: Flow fields: dense correspondence fields for highly accurate large displacement optical flow estimation. In: IEEE International Conference on Computer Vision, pp. 4015–4023 (2015)
Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M., Szeliski, R.: A database and evaluation methodology for optical flow. Int. J. Comput. Vis. 92(1), 1–31 (2011)
Bao, L., Yang, Q., Jin, H.: Fast edge-preserving patchmatch for large displacement optical flow. In: Computer Vision and Pattern Recognition (CVPR), Columbus (2014)
Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: Patchmatch: a randomized correspondence algorithm for structural image editing. ACM Trans. Graph. 28(3), 24 (2009)
Barron, J., Fleet, D., Beauchemin, S.: Evaluation of optical flow. Int. J. Comput. Vis. 12(1), 43–77 (1994)
Berkels, B., Kondermann, C., Garbe, C.S., Rumpf, M.: Reconstructing optical flow fields by motion inpainting. In: Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), pp. 388–400. Bonn, Germany (2009)
Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, pp. 417–424 (2000)
Bigun, J., Granlund, G.H., Wiklund, J.: Multidimensional orientation estimation with applications to texture analysis and optical flow. IEEE Trans. Pattern Anal. Mach. Intell. 13(8), 775–790 (1991)
Black, M., Anandan, P.: The robust estimation of multiple motions: parametric and piecewise-smooth flow fields. Comput. Vis. Image Underst. 63(1), 75–104 (1996)
Black, M.J., Anandan, P.: A framework for the robust estimation of optical flow. In: International Conference on Computer Vision (ICCV), pp. 231–236 (1993)
Black, M.J., Yacoob, Y.: Recognizing facial expressions in image sequences using local parameterized models of image motion. Int. J. Comput. Vis. 25(1), 23–48 (1997)
Bouguet, J.Y.: Pyramidal implementation of the affine lucas-kanade feature tracker description of the algorithm. Intel Corp. 5, 1–10 (2001)
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 (2011)
Braux-Zin, J., Dupont, R., Bartoli, A.: A general dense image matching framework combining direct and feature-based costs. In: International Conference on Computer Vision (ICCV) (2013)
Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: European Conference on Computer Vision (ECCV), pp. 25–36. Prague, Czech Republic (2004)
Brox, T., Malik, J.: Large displacement optical flow: descriptor matching in variational motion estimation. IEEE Trans. Pattern Anal. Mach. Intell. 33(3), 500–513 (2011)
Bruhn, A., Weickert, J., Schnörr, C.: Lucas/kanade meets horn/schunck: combining local and global optic flow methods. Int. J. Comput. Vis. 61(3), 211–231 (2005)
Bruhn, A., Weickert, W.: A confidence measure for variational optic flow methods. In: Geometric Properties for Incomplete Data, pp. 283–298 (2006)
Bugeau, A., Ta, V., Papadakis, N.: Variational exemplar-based image colorization. IEEE Trans. Image Process. 23(1), 298–307 (2014)
Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: European Conference on Computer Vision (ECCV), pp. 611–625. Springer-Verlag, Berlin (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., Kang, S.H., Shen, J.: Euler’s elastica and curvature-based inpainting. SIAM J. Appl. Math. 63, 564–592 (2002)
Chen, Y., Ye, X.: Projection Onto a Simplex. Cornell University Press, Ithaca (2011)
Chen, Z., Jin, H., Lin, Z., Cohen, S., Wu, Y.: Large displacement optical flow from nearest neighbor fields. In: Computer Vision and Pattern Recognition (CVPR), pp. 2443–2450 (2013)
Chen, Z., Wang, J., Wu, Y.: Decomposing and regularizing sparse/non-sparse components for motion field estimation. In: Computer Vision and Pattern Recognition (CVPR), pp. 1776–1783 (2012)
Corpetti, T., Mémin, E.: Stochastic uncertainty models for the luminance consistency assumption. IEEE Trans. Image Process. 21(2), 481–493 (2012)
Cremers, D., Soatto, S.: Motion competition: a variational approach to piecewise parametric motion segmentation. Int. J. Comput. Vis. 62(3), 249–265 (2005)
Criminisi, A., Pérez, P., Toyama, K.: Region filling and object removal by exemplar-based image inpainting. IEEE Trans. Image Process. 13(9), 1200–1212 (2004)
Dong, W., Shi, G., Hu, X., Ma, Y.: Nonlocal sparse and low-rank regularization for optical flow estimation. IEEE Trans. Image Process. 23(10), 4527–4538 (2014)
Enkelmann, W.: Investigations of multigrid algorithms for the estimation of optical flow fields in image sequences. Comput. Vis. Graph. Image Process. 43(2), 150–177 (1988)
Fermüller, C., Shulman, D., Aloimonos, Y.: The statistics of optical flow. Comput. Vis. Image Underst. 82(1), 1–32 (2001)
Fleet, D.J., Black, M.J., Yacoob, Y., Jepson, A.D.: Design and use of linear models for image motion analysis. Int. J. Comput. Vis. 36(3), 171–193 (2000)
Fortun, D., Bouthemy, P., Kervrann, C.: Optical flow modeling and computation: a survey. Comput. Vis. Image Underst. 134, 1–21 (2015a)
Fortun, D., Bouthemy, P., Kervrann, C.: Sparse aggregation framework for optical flow estimation. In: International Conference on Scale Space and Variational Methods in Computer Vision, pp. 323–334. Lège-Cap Ferret, France (2015b)
Fortun, D., Bouthemy, P., Kervrann, C.: Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow. Comput. Vis. Image Underst. (in press) (2016)
Fortun, D., Bouthemy, P., Paul-Gilloteaux, P., Kervrann, C.: Aggregation of patch-based estimations for illumination-invariant optical flow in live cell imaging. In: International Symposium on Biomedical Imaging (ISBI), pp. 660–663 (2013)
Galvin, B., McCane, B., Novins, K., Mason, D., Mills, S.: Recovering motion fields: an evaluation of eight optical flow algorithms. In: British Machine Vision Conference (1998)
Hafner, D., Demetz, O., Weickert, J.: Why is the census transform good for robust optic flow computation? In: Scale Space and Variational Methods in Computer Vision (SSVM), pp. 210–221 (2013)
He, K., Sun, J.: Image completion approaches using the statistics of similar patches. IEEE Trans. Pattern Anal. Mach. Intell. 36(12), 2423–2435 (2014)
Heitz, F., Bouthemy, P.: Multimodal estimation of discontinuous optical flow using markov random fields. IEEE Trans. Pattern Anal. Mach. Intell. 15(12), 1217–1232 (1993)
Horn, B., Schunck, B.: Determining optical flow. Artif. Intell. 17(1–3), 185–203 (1981)
Hornacek, M., Besse, F., Kautz, J., Fitzgibbon, A.W., Rother, C.: Highly overparameterized optical flow using patchmatch belief propagation. In: European Conference on Computer Vision, Zurich, pp. 220–234 (2014)
Humayun, A., Mac Aodha, O., Brostow, G.J.: Learning to find occlusion regions. In: Computer Vision and Pattern Recognition (CVPR), pp. 2161–2168 (2011)
Ince, S., Konrad, J.: Occlusion-aware optical flow estimation. IEEE Trans. Image Process. 17(8), 1443–1451 (2008)
Jia, K., Wang, X., Tang, X.: Optical flow estimation using learned sparse model. In: International Conference on Computer Vision (ICCV), pp. 2391–2398 (2011)
Jodoin, P.M., Mignotte, M.: Optical-flow based on an edge-avoidance procedure. Comput. Vis. Image Underst. 113(4), 511–531 (2009)
Komodakis, N., Tziritas, G.: Image completion using efficient belief propagation via priority scheduling and dynamic pruning. IEEE Trans. Image Process. 16(11), 2649–2661 (2007)
Kondermann, C., Mester, R., Garbe, C.: A statistical confidence measure for optical flows. In: European Conference on Computer Vision (ECCV), pp. 290–301. Marseille, France (2008)
Kybic, J., Nieuwenhuis, C.: Bootstrap optical flow confidence and uncertainty measure. Comput. Vis. Image Underst. 115(10), 1449–1462 (2011)
Leordeanu, M., Zanfir, A., Sminchisescu, C.: Locally affine sparse-to-dense matching for motion and occlusion estimation. In: International Conference on Computer Vision (ICCV), pp. 1221–1728. Sydney, Australia (2013)
Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 674–679 (1981)
Maurizot, M., Bouthemy, P., Delyon, B., Juditski, A., Odobez, J.M.: Determination of singular points in 2D deformable flow fields. In: International Conference on Image Processing (ICIP), vol. 3, pp. 488–491. Washington, DC (1995)
Mémin, E., Pérez, P.: Dense estimation and object-based segmentation of the optical flow with robust techniques. IEEE Trans. Image Process. 7(5), 703–719 (1998)
Menze, M., Heipke, C., Geiger, A.: Discrete optimization for optical flow. In: Pattern Recognition, pp. 16–28. Springer (2015)
Mohamed, M., Rashwan, H., Mertsching, B., Garcia, M., Puig, D.: Illumination-robust optical flow approach using local directional pattern. IEEE Trans. Circuits Syst. Video Technol. 24(9), 1499–1508 (2014)
Mota, C., Stuke, L., Barth, E.: Analytic solutions for multiple motions. In: International Conference on Image Processing (ICIP), pp. 917–920. Thessaloniki, Greece (2001)
Mozerov, M.: Constrained optical flow estimation as a matching problem. IEEE Trans. Image Process. 22(5), 2044–2055 (2013)
Nagel, H., Enkelmann, W.: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Trans. Pattern Anal. Mach. Intell. 8(5), 565–593 (1986)
Nieuwenhuis, C., Kondermann, D., Garbe, C.S.: Complex motion models for simple optical flow estimation. In: Pattern Recognition, pp. 141–150. Springer, Berlin (2010)
Odobez, J., Bouthemy, P.: Robust multiresolution estimation of parametric motion models. J. Vis. Commun. Image Represent. 6(4), 348–365 (1995)
Papadakis, N., Yildizoglu, R., Aujol, J.F., Caselles, V.: High-dimension multilabel problems: convex or nonconvex relaxation? SIAM J. Imaging Sci. 6(4), 2603–2639 (2013)
Pierre, F., Aujol, J.F., Bugeau, A., Papadakis, N., Ta, V.T.: Luminance-chrominance model for image colorization. SIAM J. Imaging Sci. 8(1), 536–563 (2015)
Pierre, F., Aujol, J.F., Bugeau, A., Ta, V.T.: Hue constrained image colorization in the rgb space. Preprint (2014)
Ranftl, R., Bredies, K., Pock, T.: Non-local total generalized variation of optical flow estimation. In: European Conference on Computer Vision, pp. 439–454. Zurich (2015)
Revaud, J., Weinzaepfel, P., Harchoui Z. Schmid, C.: Epicflow: edge-preserving interpolation of correspondences for optical flow. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15). Boston, MA (2015)
Salmon, J., Strozecki, Y.: Patch reprojections for non-local methods. Signal Process. 92(2), 477–489 (2012)
Senst, T., Eiselen, V., Sikora, T.: Robust local optical flow for feature tracking. IEEE Trans. Circuits Syst. Video Technol. 22(9), 1377–1387 (2012)
Shen, X., Wu, Y.: Sparsity model for robust optical flow estimation at motion discontinuities. In: Computer Vision and Pattern Recognition (CVPR), pp. 2456–2463 (2010)
Simoncelli, E.P., Adelson, E.H., Heeger, D.J.: Probability distributions of optical flow. In: Computer Vision and Pattern Recognition (CVPR), pp. 310–315 (1991)
Stein, A.N., Hebert, M.: Occlusion boundaries from motion: Low-level detection and mid-level reasoning. Int. J. Comput. Vis. 82(3), 325–357 (2009)
Steinbrucker, F., Pock, T., Cremers, D.: Advanced data terms for variational optic flow estimation. In: Vision, Modeling, and Visualization Workshop (2009)
Sun, D., Liu, C., Pfister, H.: Local layering for joint motion estimation and occlusion detection. In: Computer Vision and Pattern Recognition (CVPR), Colombus (2014)
Sun, D., Roth, S., Black, M.J.: A quantitative analysis of current practices in optical flow estimation and the principles behind them. Int. J. Comput. Vis. 106(2), 115–137 (2014)
Sun, D., Sudderth, E.B., Black, M.J.: Layered segmentation and optical flow estimation over time. In: Computer Vision and Pattern Recognition (CVPR), pp. 1768–1775 (2012)
Sun, J., Li, Y., Kang, S.B.: Symmetric stereo matching for occlusion handling. In: IEEE Conference on Computer Vision and Pattern (CVPR’05), pp. 399–406. San Diego, CA (2005)
Timofte, R., Gool, L.V.: Sparse flow: Sparse matching for small to large displacement optical flow. In: IEEE Winter Conference on Applications of Computer Vision, WACV, Waikoloa, HI, pp. 1100–1106 (2015)
Unger, M., Werlberger, M., Pock, T., Bischof, H.: Joint motion estimation and segmentation of complex scenes with label costs and occlusion modeling. In: Computer Vision and Pattern Recognition (CVPR), pp. 1878–1885 (2012)
Vogel, C.R., Oman, M.E.: Iterative methods for total variation denoising. SIAM J. Sci. Comput. 17(1), 227–238 (1996)
Wedel, A., Pock, T., Zach, C., Bischof, H., Cremers, D.: An improved algorithm for tv-l 1 optical flow. In: Statistical and Geometrical Approaches to Visual Motion Analysis, pp. 23–45 (2009)
Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C., et al.: Deepflow: Large displacement optical flow with deep matching. In: International Conference on Computer Vision (ICCV), pp. 1385–1392. Sydney (2013)
Werlberger, M., Pock, T., Bischof, H.: Motion estimation with non-local total variation regularization. In: Computer Vision and Pattern Recognition (CVPR’10), pp. 2464–2471. San-Fransisco (2010)
Wulff, J., Black, M.: Efficient sparse-to-dense optical flow estimation using a learned basis and layers. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15). Boston, MA (2015)
Xu, L., Jia, J., Matsushita, Y.: Motion detail preserving optical flow estimation. IEEE Trans. Pattern Anal. Mach. Intell. 34(9), 1744–1757 (2012)
Yang, J., Li, H.: Dense, accurate optical flow estimation with piecewise parametric model. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15), Boston, MA (2015)
Yang, J., Zhang, Y.: Alternating direction algorithms for \(\backslash \)ell_1-problems in compressive sensing. SIAM J. Sci. Comput. 33(1), 250–278 (2011)
Zimmer, H., Bruhn, A., Weickert, J.: Optic flow in harmony. Int. J. Comput. Vis. 93(3), 1–21 (2011)
Acknowledgments
This work was realized as part of the Quaero program, funded by OSEO, French State agency for innovation. The authors acknowledge France-BioImaging infrastructure supported by the French National Research Agency (ANR-10-INBS-04-07, “Investments for the future”). They thank also the reviewers for useful comments helping improving the paper. Finally, they thank Ferreol Soulez, Martin Storath, Olivier Demetz, Simon Setzer and Joachim Weickert for inspiring discussions at different stages of this work.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Fortun, D., Bouthemy, P. & Kervrann, C. A Variational Aggregation Framework for Patch-Based Optical Flow Estimation. J Math Imaging Vis 56, 280–299 (2016). https://doi.org/10.1007/s10851-016-0664-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-016-0664-6