Multidimensional Orientation Estimation with Applications to Texture Analysis and Optical Flow
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computing Optical Flow with Physical Models of Brightness Variation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer Vision and Image Understanding - Special issue on empirical evaluation of computer vision algorithms
Learning Parameterized Models of Image Motion
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Learned Temporal Models of Image Motion
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
On the Spatial Statistics of Optical Flow
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
A Low Dimensional Fluid Motion Estimator
International Journal of Computer Vision
Over-Parameterized Variational Optical Flow
International Journal of Computer Vision
Postprocessing of Optical Flows Via Surface Measures and Motion Inpainting
Proceedings of the 30th DAGM symposium on Pattern Recognition
Optimal filters for extended optical flow
IWCM'04 Proceedings of the 1st international conference on Complex motion
An adaptive confidence measure for optical flows based on linear subspace projections
Proceedings of the 29th DAGM conference on Pattern recognition
Physically consistent and efficient variational denoising of image fluid flow estimates
IEEE Transactions on Image Processing
Variational optical flow computation in real time
IEEE Transactions on Image Processing
Hi-index | 0.00 |
The selection of an optical flow method is mostly a choice from among accuracy, efficiency and ease of implementation. While variational approaches tend to be more accurate than local parametric methods, much algorithmic effort and expertise is often required to obtain comparable efficiency with the latter. Through the exploitation of natural motion statistics, the estimation of optical flow from local parametric models yields a good alternative. We show that learned, linear, parametric models capture specific higher order relations between neighboring flow vectors and, thus, allow for complex, spatio-temporal motion patterns despite a simple and efficient implementation. The method comes with an inherent confidence measure, and the motion models can easily be adapted to specific applications with typical motion patterns by choice of training data. The proposed approach can be understood as a generalization of the original structure tensor approach to the incorporation of arbitrary linear motion models. In this way accuracy, specificity, efficiency and ease of implementation can be achieved at the same time.