An Unbiased Second-Order Prior for High-Accuracy Motion Estimation

Authors:
Werner Trobin;Thomas Pock;Daniel Cremers;Horst Bischof
Affiliations:
Institute for Computer Graphics and Vision, Graz University of Technology,;Institute for Computer Graphics and Vision, Graz University of Technology, and Department of Computer Science, University of Bonn,;Department of Computer Science, University of Bonn,;Institute for Computer Graphics and Vision, Graz University of Technology,
Venue:
Proceedings of the 30th DAGM symposium on Pattern Recognition
Year:
2008

Citing 11
Cited 8

An Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image Sequences

IEEE Transactions on Pattern Analysis and Machine Intelligence
Nonlinear total variation based noise removal algorithms

Proceedings of the eleventh annual international conference of the Center for Nonlinear Studies on Experimental mathematics : computational issues in nonlinear science: computational issues in nonlinear science
Computing optical flow via variational techniques

SIAM Journal on Applied Mathematics
Skin and Bones: Multi-layer, Locally Affine, Optical Flow and Regularization with Transparency

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Highly Accurate Optic Flow Computation with Theoretically Justified Warping

International Journal of Computer Vision
A Multigrid Platform for Real-Time Motion Computation with Discontinuity-Preserving Variational Methods

International Journal of Computer Vision
Simultaneous Higher-Order Optical Flow Estimation and Decomposition

SIAM Journal on Scientific Computing
Over-Parameterized Variational Optical Flow

International Journal of Computer Vision
A duality based approach for realtime TV-L1 optical flow

Proceedings of the 29th DAGM conference on Pattern recognition
Total absolute Gaussian curvature for stereo prior

ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
Total variation minimization and a class of binary MRF models

EMMCVPR'05 Proceedings of the 5th international conference on Energy Minimization Methods in Computer Vision and Pattern Recognition

Total-Variation Based Piecewise Affine Regularization

SSVM '09 Proceedings of the Second International Conference on Scale Space and Variational Methods in Computer Vision
Optical Flow Computation from an Asynchronised Multiresolution Image Sequence

ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
Two Step Variational Method for Subpixel Optical Flow Computation

ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part II
A Database and Evaluation Methodology for Optical Flow

International Journal of Computer Vision
Shape prior embedded geodesic distance transform for image segmentation

ACCV'10 Proceedings of the 2010 international conference on Computer vision - Volume part II
Improving sub-pixel correspondence through upsampling

Computer Vision and Image Understanding
Over-Parameterized optical flow using a stereoscopic constraint

SSVM'11 Proceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision
High accuracy TOF and stereo sensor fusion at interactive rates

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

Virtually all variational methods for motion estimation regularize the gradient of the flow field, which introduces a bias towards piecewise constant motions in weakly textured areas. We propose a novel regularization approach, based on decorrelated second-order derivatives, that does not suffer from this shortcoming. We then derive an efficient numerical scheme to solve the new model using projected gradient descent. A comparison to a TV regularized model shows that the proposed second-order prior exhibits superior performance, in particular in low-textured areas (where the prior becomes important). Finally, we show that the proposed model yields state-of-the-art results on the Middlebury optical flow database.