Learning high-order MRF priors of color images
ICML '06 Proceedings of the 23rd international conference on Machine learning
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 adaptive confidence measure for optical flows based on linear subspace projections
Proceedings of the 29th DAGM conference on Pattern recognition
Independent component analysis of layer optical flow and its application
BVAI'07 Proceedings of the 2nd international conference on Advances in brain, vision and artificial intelligence
Smoothing of optical flow using robustified diffusion kernels
Image and Vision Computing
Complex motion models for simple optical flow estimation
Proceedings of the 32nd DAGM conference on Pattern recognition
Variational method for super-resolution optical flow
Signal Processing
Dense versus Sparse Approaches for Estimating the Fundamental Matrix
International Journal of Computer Vision
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Efficient scale-space spatiotemporal saliency tracking for distortion-free video retargeting
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
On performance analysis of optical flow algorithms
Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis
Registration using sparse free-form deformations
MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II
Lessons and insights from creating a synthetic optical flow benchmark
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume 2
On line background modeling for moving object segmentation in dynamic scenes
Multimedia Tools and Applications
A Novel Space Variant Image Representation
Journal of Mathematical Imaging and Vision
Hi-index | 0.00 |
We develop a method for learning the spatial statistics of optical flow fields from a novel training database. Training flow fields are constructed using range images of natural scenes and 3D camera motions recovered from hand-held and car-mounted video sequences. A detailed analysis of optical flow statistics in natural scenes is presented and machine learning methods are developed to learn a Markov random field model of optical flow. The prior probability of a flow field is formulated as a Field-of-Experts model that captures the higher order spatial statistics in overlapping patches and is trained using contrastive divergence. This new optical flow prior is compared with previous robust priors and is incorporated into a recent, accurate algorithm for dense optical flow computation. Experiments with natural and synthetic sequences illustrate how the learned optical flow prior quantitatively improves flow accuracy and how it captures the rich spatial structure found in natural scene motion.