Search For:

Displaying 1-21 out of 21 total
Shrinkage Fields for Effective Image Restoration
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Uwe Schmidt,Stefan Roth
Issue Date:June 2014
pp. 2774-2781
Many state-of-the-art image restoration approaches do not scale well to larger images, such as megapixel images common in the consumer segment. Computationally expensive optimization is often the culprit. While efficient alternatives exist, they have not r...
 
Learning People Detectors for Tracking in Crowded Scenes
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Siyu Tang,Mykhaylo Andriluka,Anton Milan,Konrad Schindler,Stefan Roth,Bernt Schiele
Issue Date:December 2013
pp. 1049-1056
People tracking in crowded real-world scenes is challenging due to frequent and long-term occlusions. Recent tracking methods obtain the image evidence from object (people) detectors, but typically use off-the-shelf detectors and treat them as black box co...
 
Piecewise Rigid Scene Flow
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Christoph Vogel,Konrad Schindler,Stefan Roth
Issue Date:December 2013
pp. 1377-1384
Estimating dense 3D scene flow from stereo sequences remains a challenging task, despite much progress in both classical disparity and 2D optical flow estimation. To overcome the limitations of existing techniques, we introduce a novel model that represent...
 
3D scene flow estimation with a rigid motion prior
Found in: Computer Vision, IEEE International Conference on
By Christoph Vogel,Konrad Schindler,Stefan Roth
Issue Date:November 2011
pp. 1291-1298
We present an approach to 3D scene flow estimation, which exploits that in realistic scenarios image motion is frequently dominated by observer motion and independent, but rigid object motion. We cast the dense estimation of both scene structure and 3D mot...
 
Monocular 3D pose estimation and tracking by detection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Mykhaylo Andriluka, Stefan Roth, Bernt Schiele
Issue Date:June 2010
pp. 623-630
Automatic recovery of 3D human pose from monocular image sequences is a challenging and important research topic with numerous applications. Although current methods are able to recover 3D pose for a single person in controlled environments, they are sever...
 
A generative perspective on MRFs in low-level vision
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Uwe Schmidt, Qi Gao, Stefan Roth
Issue Date:June 2010
pp. 1751-1758
Markov random fields (MRFs) are popular and generic probabilistic models of prior knowledge in low-level vision. Yet their generative properties are rarely examined, while application-specific models and non-probabilistic learning are gaining increased att...
 
Secrets of optical flow estimation and their principles
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Deqing Sun, Stefan Roth, Michael J. Black
Issue Date:June 2010
pp. 2432-2439
The accuracy of optical flow estimation algorithms has been improving steadily as evidenced by results on the Middlebury optical flow benchmark. The typical formulation, however, has changed little since the work of Horn and Schunck. We attempt to uncover ...
 
Automatic discovery of meaningful object parts with latent CRFs
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Paul Schnitzspan, Stefan Roth, Bernt Schiele
Issue Date:June 2010
pp. 121-128
Object recognition is challenging due to high intra-class variability caused, e.g., by articulation, viewpoint changes, and partial occlusion. Successful methods need to strike a balance between being flexible enough to model such variation and discriminat...
 
Fusion Moves for Markov Random Field Optimization
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Victor Lempitsky, Carsten Rother, Stefan Roth, Andrew Blake
Issue Date:August 2010
pp. 1392-1405
The efficient application of graph cuts to Markov Random Fields (MRFs) with multiple discrete or continuous labels remains an open question. In this paper, we demonstrate one possible way of achieving this by using graph cuts to combine pairs of suboptimal...
 
FusionFlow: Discrete-continuous optimization for optical flow estimation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Victor Lempitsky, Stefan Roth, Carsten Rother
Issue Date:June 2008
pp. 1-8
Accurate estimation of optical flow is a challenging task, which often requires addressing difficult energy optimization problems. To solve them, most top-performing methods rely on continuous optimization algorithms. The modeling accuracy of the energy in...
 
People-tracking-by-detection and people-detection-by-tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Mykhaylo Andriluka, Stefan Roth, Bernt Schiele
Issue Date:June 2008
pp. 1-8
Both detection and tracking people are challenging problems, especially in complex real world scenes that commonly involve multiple people, complicated occlusions, and cluttered or even moving backgrounds. People detectors have been shown to be able to loc...
 
A Database and Evaluation Methodology for Optical Flow
Found in: Computer Vision, IEEE International Conference on
By Simon Baker, Stefan Roth, Daniel Scharstein, Michael J. Black, J.P. Lewis, Richard Szeliski
Issue Date:October 2007
pp. 1-8
The quantitative evaluation of optical flow algorithms by Barron et al. led to significant advances in the performance of optical flow methods. The challenges for optical flow today go beyond the datasets and evaluation methods proposed in that paper and c...
 
Specular Flow and the Recovery of Surface Structure
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Stefan Roth, Michael J. Black
Issue Date:June 2006
pp. 1869-1876
In scenes containing specular objects, the image motion observed by a moving camera may be an intermixed combination of optical flow resulting from diffuse reflectance (diffuse flow) and specular reflection (specular flow). Here, with few assumptions, we f...
 
On the Spatial Statistics of Optical Flow
Found in: Computer Vision, IEEE International Conference on
By Stefan Roth, Michael J. Black
Issue Date:October 2005
pp. 42-49
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 se...
 
Fields of Experts: A Framework for Learning Image Priors
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Stefan Roth, Michael J. Black
Issue Date:June 2005
pp. 860-867
We develop a framework for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks. The approach extends traditional Markov Random Field (MRF) models by learning potentia...
 
Tracking Loose-Limbed People
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Leonid Sigal, Sidharth Bhatia, Stefan Roth, Michael J Black, Michael Isard
Issue Date:July 2004
pp. 421-428
We pose the problem of 3D human tracking as one of inference in a graphical model. Unlike traditional kinematic tree representations, our model of the body is a collection of loosely-connected limbs. Conditional probabilities relating the 3D pose of connec...
 
Continuous Energy Minimization for Multitarget Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Anton Milan,Stefan Roth,Konrad Schindler
Issue Date:January 2014
pp. 58-72
Many recent advances in multiple target tracking aim at finding a (nearly) optimal set of trajectories within a temporal window. To handle the large space of possible trajectory hypotheses, it is typically reduced to a finite set by some form of data-drive...
 
Detection- and Trajectory-Level Exclusion in Multiple Object Tracking
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Anton Milan,Konrad Schindler,Stefan Roth
Issue Date:June 2013
pp. 3682-3689
When tracking multiple targets in crowded scenarios, modeling mutual exclusion between distinct targets becomes important at two levels: (1) in data association, each target observation should support at most one trajectory and each trajectory should be as...
 
Discriminative Non-blind Deblurring
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Uwe Schmidt,Carsten Rother,Sebastian Nowozin,Jeremy Jancsary,Stefan Roth
Issue Date:June 2013
pp. 604-611
Non-blind deblurring is an integral component of blind approaches for removing image blur due to camera shake. Even though learning-based deblurring methods exist, they have been limited to the generative case and are computationally expensive. To this dat...
 
Steerable Random Fields
Found in: Computer Vision, IEEE International Conference on
By Stefan Roth, Michael J. Black
Issue Date:October 2007
pp. 1-8
In contrast to traditional Markov random field (MRF) models, we develop a Steerable Random Field (SRF) in which the field potentials are defined in terms of filter responses that are steered to the local image structure. In particular, we use the structure...
 
Gibbs Likelihoods for Bayesian Tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Stefan Roth, Leonid Sigal, Michael J. Black
Issue Date:July 2004
pp. 886-893
Bayesian methods for visual tracking model the likelihood of image measurements conditioned on a tracking hypothesis. Image measurements may, for example, correspond to various filter responses at multiple scales and orientations. Most tracking approaches ...
 
 1