Depth Discontinuities by Pixel-to-Pixel Stereo
International Journal of Computer Vision
The Geometry of Multiple Images: The Laws That Govern The Formation of Images of A Scene and Some of Their Applications
Hierarchical Estimation and Segmentation of Dense Motion Fields
International Journal of Computer Vision
Hierarchical Model-Based Motion Estimation
ECCV '92 Proceedings of the Second European Conference on Computer Vision
A Common Framework for Curve Evolution, Segmentation and Anisotropic Diffusion
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
Variational Stereovision and 3D Scene Flow Estimation with Statistical Similarity Measures
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Lucas/Kanade meets Horn/Schunck: combining local and global optic flow methods
International Journal of Computer Vision
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
Piecewise-Smooth Dense Optical Flow via Level Sets
International Journal of Computer Vision
Coarse to over-fine optical flow estimation
Pattern Recognition
On the Spatial Statistics of Optical Flow
International Journal of Computer Vision
Over-Parameterized Variational Optical Flow
International Journal of Computer Vision
A Variational Model for the Joint Recovery of the Fundamental Matrix and the Optical Flow
Proceedings of the 30th DAGM symposium on Pattern Recognition
An Unbiased Second-Order Prior for High-Accuracy Motion Estimation
Proceedings of the 30th DAGM symposium on Pattern Recognition
Is Dense Optic Flow Useful to Compute the Fundamental Matrix?
ICIAR '08 Proceedings of the 5th international conference on Image Analysis and Recognition
Stereo Matching Using Population-Based MCMC
International Journal of Computer Vision
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Detection of Intensity and Motion Edges within Optical Flow via Multidimensional Control
SIAM Journal on Imaging Sciences
Fusion Moves for Markov Random Field Optimization
IEEE Transactions on Pattern Analysis and Machine Intelligence
Stereo Matching with Mumford-Shah Regularization and Occlusion Handling
IEEE Transactions on Pattern Analysis and Machine Intelligence
PR'05 Proceedings of the 27th DAGM conference on Pattern Recognition
Group-Valued regularization for analysis of articulated motion
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
Hi-index | 0.00 |
The success of variational methods for optical flow computation lies in their ability to regularize the problem at a differential (pixel) level and combine piecewise smoothness of the flow field with the brightness constancy assumptions. However, the piecewise smoothness assumption is often motivated by heuristic or algorithmic considerations. Lately, new priors were proposed to exploit the structural properties of the flow. Yet, most of them still utilize a generic regularization term. In this paper we consider optical flow estimation in static scenes. We show that introducing a suitable motion model for the optical flow allows us to pose the regularization term as a geometrically meaningful one. The proposed method assumes that the visible surface can be approximated by a piecewise smooth planar manifold. Accordingly, the optical flow between two consecutive frames can be locally regarded as a homography consistent with the epipolar geometry and defined by only three parameters at each pixel. These parameters are directly related to the equation of the scene local tangent plane, so that their spatial variations should be relatively small, except for creases and depth discontinuities. This leads to a regularization term that measures the total variation of the model parameters and can be extended to a Mumford-Shah segmentation of the visible surface. This new technique yields significant improvements over state of the art optical flow computation methods for static scenes.