Adaptive Discretizations for Non-smooth Variational Vision

Variational problems in vision are solved numerically on the pixel lattice because it provides the simplest computational grid to discretize the input images, even though a uniform grid seldom matches the complexity of the solution. To adapt the complexity of the discretization to the solution, it is necessary to adopt finite-element techniques that match the resolution of piecewise polynomial bases to the resolving power of the variational model, but such techniques have been overlooked for nonsmooth variational models. To address this issue, we investigate the pros and cons of finite-element discretizations for nonsmooth variational problems in vision, their multiresolution properties, and the optimization algorithms to solve them. Our 2 and 3D experiments in image segmentation, optical flow, stereo, and depth fusion reveal the conditions where finite-element can outperform finite-difference discretizations by achieving significant computational savings with a minor loss of accuracy.

[1]  Daniel Cremers,et al.  An Improved Algorithm for TV-L 1 Optical Flow , 2009, Statistical and Geometrical Approaches to Visual Motion Analysis.

[2]  Thomas Brox,et al.  Global, Dense Multiscale Reconstruction for a Billion Points , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[3]  Martin Rumpf,et al.  An Adaptive Finite Element Method for Large Scale Image Processing , 2000, J. Vis. Commun. Image Represent..

[4]  Christoph Schnörr,et al.  A Study of a Convex Variational Diffusion Approach for Image Segmentation and Feature Extraction , 1998, Journal of Mathematical Imaging and Vision.

[5]  Daniel Cremers,et al.  Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation , 2005, International Journal of Computer Vision.

[6]  Jan-Michael Frahm,et al.  Real-Time Visibility-Based Fusion of Depth Maps , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[7]  Xavier Bresson,et al.  Geometric Applications of the Split Bregman Method: Segmentation and Surface Reconstruction , 2010, J. Sci. Comput..

[8]  Martin Rumpf,et al.  An Adaptive Finite Element Method for Large Scale Image Processing , 1999, J. Vis. Commun. Image Represent..

[9]  Isabelle Herlin,et al.  Non uniform multiresolution method for optical flow computation , 1996 .

[10]  Gabriel Taubin,et al.  SSD: Smooth Signed Distance Surface Reconstruction , 2011, Comput. Graph. Forum.

[11]  Michael M. Kazhdan,et al.  Screened poisson surface reconstruction , 2013, TOGS.

[12]  Horst Bischof,et al.  Online 3D reconstruction using convex optimization , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

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

[14]  Ming C. Lin,et al.  Example-guided physically based modal sound synthesis , 2013, ACM Trans. Graph..

[15]  K. Mikula,et al.  A coarsening finite element strategy in image selective smoothing , 1997 .

[16]  Michael J. Black,et al.  Secrets of optical flow estimation and their principles , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  L. Piegl,et al.  The NURBS Book , 1995, Monographs in Visual Communications.

[18]  Heinrich Niemann,et al.  Finite element method for determination of optical flow , 1992, Pattern Recognit. Lett..

[19]  Jonathan Balzer,et al.  Isogeometric finite-elements methods and variational reconstruction tasks in vision — A perfect match , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Alfred M. Bruckstein,et al.  Over-Parameterized Variational Optical Flow , 2007, International Journal of Computer Vision.

[21]  Dan Givoli,et al.  An adaptive finite element procedure for the image segmentation problem , 1998 .

[22]  Patrick L. Combettes,et al.  Proximal Splitting Methods in Signal Processing , 2009, Fixed-Point Algorithms for Inverse Problems in Science and Engineering.

[23]  Horst Bischof,et al.  A Globally Optimal Algorithm for Robust TV-L1 Range Image Integration , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[24]  Michael Scott,et al.  Robust Poisson Surface Reconstruction , 2015, SSVM.

[25]  Jiaolong Yang,et al.  Dense, accurate optical flow estimation with piecewise parametric model , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Malcolm A. Sabin,et al.  Non-uniform recursive subdivision surfaces , 1998, SIGGRAPH.

[27]  Konrad Schindler,et al.  Piecewise Rigid Scene Flow , 2013, 2013 IEEE International Conference on Computer Vision.

[28]  Michael J. Black,et al.  Layered segmentation and optical flow estimation over time , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Mila Nikolova,et al.  Algorithms for Finding Global Minimizers of Image Segmentation and Denoising Models , 2006, SIAM J. Appl. Math..

[30]  Markus Vincze,et al.  Direct Optimization of T-Splines Based on Multiview Stereo , 2014, 2014 2nd International Conference on 3D Vision.