Timezone: »
Layered models are a powerful way of describing natural scenes containing smooth surfaces that may overlap and occlude each other. For image motion estimation, such models have a long history but have not achieved the wide use or accuracy of non-layered methods. We present a new probabilistic model of optical flow in layers that addresses many of the shortcomings of previous approaches. In particular, we define a probabilistic graphical model that explicitly captures: 1) occlusions and disocclusions; 2) depth ordering of the layers; 3) temporal consistency of the layer segmentation. Additionally the optical flow in each layer is modeled by a combination of a parametric model and a smooth deviation based on an MRF with a robust spatial prior; the resulting model allows roughness in layers. Finally, a key contribution is the formulation of the layers using an image-dependent hidden field prior based on recent models for static scene segmentation. The method achieves state-of-the-art results on the Middlebury benchmark and produces meaningful scene segmentations as well as detected occlusion regions.
Author Information
Deqing Sun (Brown University)
Erik Sudderth (University of California, Irvine)
Michael J Black (Max Planck Institute for Intelligent Systems)
Related Events (a corresponding poster, oral, or spotlight)
-
2010 Poster: Layered image motion with explicit occlusions, temporal consistency, and depth ordering »
Mon. Dec 6th 08:00 -- 08:00 AM Room
More from the Same Authors
-
2021 Poster: Scalable and Stable Surrogates for Flexible Classifiers with Fairness Constraints »
Henry C Bendekgey · Erik Sudderth -
2015 Poster: Scalable Adaptation of State Complexity for Nonparametric Hidden Markov Models »
Michael Hughes · William Stephenson · Erik Sudderth -
2013 Poster: Efficient Online Inference for Bayesian Nonparametric Relational Models »
Dae Il Kim · Prem Gopalan · David Blei · Erik Sudderth -
2013 Poster: Memoized Online Variational Inference for Dirichlet Process Mixture Models »
Michael Hughes · Erik Sudderth -
2012 Poster: Effective Split-Merge Monte Carlo Methods for Nonparametric Models of Sequential Data »
Michael Hughes · Emily Fox · Erik Sudderth -
2012 Poster: Truly Nonparametric Online Variational Inference for Hierarchical Dirichlet Processes »
Michael Bryant · Erik Sudderth -
2012 Poster: Minimization of Continuous Bethe Approximations: A Positive Variation »
Jason Pacheco · Erik Sudderth -
2012 Poster: From Deformations to Parts: Motion-based Segmentation of 3D Objects »
Soumya Ghosh · Erik Sudderth · Matthew Loper · Michael J Black -
2012 Poster: A Geometric take on Metric Learning »
Søren Hauberg · Oren Freifeld · Michael J Black -
2011 Poster: The Doubly Correlated Nonparametric Topic Model »
Dae Il Kim · Erik Sudderth -
2011 Poster: Spatial distance dependent Chinese Restaurant Process for image segmentation »
Soumya Ghosh · Andrei B Ungureanu · Erik Sudderth · David Blei -
2010 Poster: Global seismic monitoring as probabilistic inference »
Nimar Arora · Stuart J Russell · Paul Kidwell · Erik Sudderth -
2009 Session: Oral session 9: Bayesian Analysis »
Erik Sudderth -
2009 Poster: Sharing Features among Dynamical Systems with Beta Processes »
Emily Fox · Erik Sudderth · Michael Jordan · Alan S Willsky -
2009 Oral: Sharing Features among Dynamical Systems with Beta Processes »
Emily Fox · Erik Sudderth · Michael Jordan · Alan S Willsky -
2009 Poster: An Additive Latent Feature Model for Transparent Object Recognition »
Mario J Fritz · Michael J Black · Gary R Bradski · Trevor Darrell -
2009 Oral: An Additive Latent Feature Model for Transparent Object Recognition »
Mario J Fritz · Michael J Black · Gary R Bradski · Trevor Darrell -
2008 Oral: Shared Segmentation of Natural Scenes Using Dependent Pitman-Yor Processes »
Erik Sudderth · Michael Jordan -
2008 Poster: Nonparametric Bayesian Learning of Switching Linear Dynamical Systems »
Emily Fox · Erik Sudderth · Michael Jordan · Alan S Willsky -
2008 Poster: Shared Segmentation of Natural Scenes Using Dependent Pitman-Yor Processes »
Erik Sudderth · Michael Jordan -
2008 Spotlight: Nonparametric Bayesian Learning of Switching Linear Dynamical Systems »
Emily Fox · Erik Sudderth · Michael Jordan · Alan S Willsky -
2008 Session: Oral session 4: Combinatorial Approximation »
Erik Sudderth -
2007 Poster: Combined discriminative and generative articulated pose and non-rigid shape estimation »
Leonid Sigal · Alexandru Balan · Michael J Black -
2007 Spotlight: Combined discriminative and generative articulated pose and non-rigid shape estimation »
Leonid Sigal · Alexandru Balan · Michael J Black -
2007 Session: Session 1: Structured Statistical Models »
Michael J Black -
2007 Poster: Loop Series and Bethe Variational Bounds in Attractive Graphical Models »
Erik Sudderth · Martin J Wainwright · Alan S Willsky -
2006 Workshop: EHuM: Evaluation of Articulated Human Motion and Pose Estimation »
Leonid Sigal · Ming-Hsuan Yang · Michael J Black -
2006 Poster: Nonlinear physically-based models for decoding motor-cortical population activity »
Gregory Shakhnarovich · Sung-Phil Kim · Michael J Black