Unbalanced Optimal Transport Regularization for Imaging Problems

The modeling of phenomenological structure is a crucial aspect in inverse imaging problems. One emerging modeling tool in computer vision is the optimal transport framework. Its ability to model geometric displacements across an image's support gives it attractive qualities similar to optical flow methods that are effective at capturing visual motion, but are restricted to operate in significantly smaller state-spaces. Despite this advantage, two major drawbacks make it unsuitable for general deployment: (i) it suffers from exorbitant computational costs due to a quadratic optimization-variable complexity, and (ii) it has a mass-balancing assumption that limits applications with natural images. We tackle these issues simultaneously by proposing a novel formulation for an unbalanced optimal transport regularizer that has linear optimization-variable complexity. In addition, we present a general proximal method for this regularizer, and demonstrate superior empirical performance on novel dynamical tracking applications in synthetic and real video.

[1]  Marco Cuturi,et al.  Sinkhorn Distances: Lightspeed Computation of Optimal Transport , 2013, NIPS.

[2]  Leonidas J. Guibas,et al.  The Earth Mover's Distance as a Metric for Image Retrieval , 2000, International Journal of Computer Vision.

[3]  Gabriel Peyré,et al.  Computational Optimal Transport , 2018, Found. Trends Mach. Learn..

[4]  Wotao Yin,et al.  A Parallel Method for Earth Mover’s Distance , 2018, J. Sci. Comput..

[5]  John Wright,et al.  Compressive principal component pursuit , 2012, 2012 IEEE International Symposium on Information Theory Proceedings.

[6]  D. Kinderlehrer,et al.  THE VARIATIONAL FORMULATION OF THE FOKKER-PLANCK EQUATION , 1996 .

[7]  Stephen P. Boyd,et al.  Proximal Algorithms , 2013, Found. Trends Optim..

[8]  Stanley Osher,et al.  Unnormalized optimal transport , 2019, J. Comput. Phys..

[9]  Aswin C. Sankaranarayanan,et al.  SpaRCS: Recovering low-rank and sparse matrices from compressive measurements , 2011, NIPS.

[10]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[11]  Georgios B. Giannakis,et al.  Doubly Robust Smoothing of Dynamical Processes via Outlier Sparsity Constraints , 2011, IEEE Transactions on Signal Processing.

[12]  Giuseppe Savaré,et al.  Optimal Entropy-Transport problems and a new Hellinger–Kantorovich distance between positive measures , 2015, 1508.07941.

[13]  Stanley Osher,et al.  Unbalanced and Partial $$L_1$$L1 Monge–Kantorovich Problem: A Scalable Parallel First-Order Method , 2018, J. Sci. Comput..

[14]  Xiaowei Zhou,et al.  Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank Representation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Kun Li,et al.  Foreground–Background Separation From Video Clips via Motion-Assisted Matrix Restoration , 2015, IEEE Transactions on Circuits and Systems for Video Technology.

[16]  William C. Davidon,et al.  Variable Metric Method for Minimization , 1959, SIAM J. Optim..

[17]  E. Mainini A description of transport cost for signed measures , 2012 .

[18]  Christopher J. Rozell,et al.  Earth-Mover's distance as a tracking regularizer , 2017, 2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP).

[19]  Christopher J. Rozell,et al.  Efficient Tracking of Sparse Signals via an Earth Mover's Distance Dynamics Regularizer , 2018, IEEE Signal Processing Letters.

[20]  Johan Karlsson,et al.  Generalized Sinkhorn Iterations for Regularizing Inverse Problems Using Optimal Mass Transport , 2016, SIAM J. Imaging Sci..

[21]  M. Salman Asif,et al.  Dynamic Updating for ` 1 Minimization , 2009 .

[22]  José M. Bioucas-Dias,et al.  Fast Image Recovery Using Variable Splitting and Constrained Optimization , 2009, IEEE Transactions on Image Processing.

[23]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[24]  Lénaïc Chizat,et al.  Scaling Algorithms for Unbalanced Transport Problems , 2016, 1607.05816.

[25]  Christophe Andrieu,et al.  Bayesian sequential compressed sensing in sparse dynamical systems , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[26]  G. Carlier,et al.  Tomographic Reconstruction from a Few Views: A Multi-Marginal Optimal Transport Approach , 2017 .

[27]  Yi Ma,et al.  Robust principal component analysis? , 2009, JACM.

[28]  D. Donoho,et al.  Sparse nonnegative solution of underdetermined linear equations by linear programming. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[29]  Karl-Theodor Sturm,et al.  Heat flow with Dirichlet boundary conditions via optimal transport and gluing of metric measure spaces , 2018, Calculus of Variations and Partial Differential Equations.

[30]  Arthur Cayley,et al.  The Collected Mathematical Papers: On Monge's “Mémoire sur la théorie des déblais et des remblais” , 2009 .

[31]  L. Kantorovich On a Problem of Monge , 2006 .

[32]  Antonin Chambolle,et al.  A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging , 2011, Journal of Mathematical Imaging and Vision.

[33]  R. Rockafellar Monotone Operators and the Proximal Point Algorithm , 1976 .

[34]  R. McCann,et al.  Free boundaries in optimal transport and Monge-Ampere obstacle problems , 2010 .

[35]  M. Beckmann A Continuous Model of Transportation , 1952 .

[36]  Gabriel Peyré,et al.  Entropic Approximation of Wasserstein Gradient Flows , 2015, SIAM J. Imaging Sci..

[37]  Emmanuel J. Candès,et al.  Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information , 2004, IEEE Transactions on Information Theory.

[38]  Xiaodong Li,et al.  Stable Principal Component Pursuit , 2010, 2010 IEEE International Symposium on Information Theory.

[39]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[40]  P. Lions,et al.  Splitting Algorithms for the Sum of Two Nonlinear Operators , 1979 .

[41]  Namrata Vaswani,et al.  LS-CS-Residual (LS-CS): Compressive Sensing on Least Squares Residual , 2009, IEEE Transactions on Signal Processing.

[42]  José M. Bioucas-Dias,et al.  An Augmented Lagrangian Approach to the Constrained Optimization Formulation of Imaging Inverse Problems , 2009, IEEE Transactions on Image Processing.

[43]  Jonathan Eckstein Splitting methods for monotone operators with applications to parallel optimization , 1989 .

[44]  C. Villani Topics in Optimal Transportation , 2003 .

[45]  A. Figalli The Optimal Partial Transport Problem , 2010 .

[46]  Christopher J. Rozell,et al.  Sparse Dynamic Filtering via Earth Mover's Distance Regularization , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[47]  Marco Cuturi,et al.  Wasserstein regularization for sparse multi-task regression , 2018, AISTATS.

[48]  Mário A. T. Figueiredo,et al.  Gradient Projection for Sparse Reconstruction: Application to Compressed Sensing and Other Inverse Problems , 2007, IEEE Journal of Selected Topics in Signal Processing.