EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
A nonparametric regression model for virtual humans generation
Multimedia Tools and Applications
Dynamic color flow: a motion-adaptive color model for object segmentation in video
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
A Database and Evaluation Methodology for Optical Flow
International Journal of Computer Vision
Control of the Effects of Regularization on Variational Optic Flow Computations
Journal of Mathematical Imaging and Vision
International Journal of Computer Vision
Object flow: learning object displacement
ACCV'10 Proceedings of the 2010 international conference on Computer vision - Volume Part I
Computing range flow from multi-modal Kinect data
ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part I
Video motion estimation with temporal coherence
Proceedings of the 10th International Conference on Virtual Reality Continuum and Its Applications in Industry
Dense versus Sparse Approaches for Estimating the Fundamental Matrix
International Journal of Computer Vision
Improving motion estimation using image-driven functions and hybrid scheme
PSIVT'11 Proceedings of the 5th Pacific Rim conference on Advances in Image and Video Technology - Volume Part I
Robust optic-flow estimation with bayesian inference of model and hyper-parameters
SSVM'11 Proceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision
Lightweight binocular facial performance capture under uncontrolled lighting
ACM Transactions on Graphics (TOG) - Proceedings of ACM SIGGRAPH Asia 2012
Efficient nonlocal regularization for optical flow
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
A naturalistic open source movie for optical flow evaluation
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
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
3D modelling of static environments using multiple spherical stereo
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part II
ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part II
Consistent Binocular Depth and Scene Flow with Chained Temporal Profiles
International Journal of Computer Vision
3D Scene Reconstruction from Multiple Spherical Stereo Pairs
International Journal of Computer Vision
The Visual Computer: International Journal of Computer Graphics
International Journal of Computer Vision
Hi-index | 0.00 |
Assumptions of brightness constancy and spatial smoothness underlie most optical flow estimation methods. In contrast to standard heuristic formulations, we learn a statistical model of both brightness constancy error and the spatial properties of optical flow using image sequences with associated ground truth flow fields. The result is a complete probabilistic model of optical flow. Specifically, the ground truth enables us to model how the assumption of brightness constancy is violated in naturalistic sequences, resulting in a probabilistic model of "brightness inconstancy". We also generalize previous high-order constancy assumptions, such as gradient constancy, by modeling the constancy of responses to various linear filters in a high-order random field framework. These filters are free variables that can be learned from training data. Additionally we study the spatial structure of the optical flow and how motion boundaries are related to image intensity boundaries. Spatial smoothness is modeled using a Steerable Random Field, where spatial derivatives of the optical flow are steered by the image brightness structure. These models provide a statistical motivation for previous methods and enable the learning of all parameters from training data. All proposed models are quantitatively compared on the Middlebury flow dataset.