Search For:

Displaying 1-41 out of 41 total
Motion Field Estimation from Alternate Exposure Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Anita Sellent, Martin Eisemann, Bastian Goldlücke, Daniel Cremers, Marcus Magnor
Issue Date:August 2011
pp. 1577-1589
Traditional optical flow algorithms rely on consecutive short-exposed images. In this work, we make use of an additional long-exposed image for motion field estimation. Long-exposed images integrate motion information directly in the form of motion-blur. W...
 
A Convex Relaxation Approach to Space Time Multi-view 3D Reconstruction
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Martin R. Oswald,Daniel Cremers
Issue Date:December 2013
pp. 291-298
We propose a convex relaxation approach to space-time 3D reconstruction from multiple videos. Generalizing the works Unger et al. [16], Kolev et al. [8] to the 4D setting, we cast the problem of reconstruction over time as a binary labeling problem in a 4D...
 
Convex Optimization for Scene Understanding
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Mohamed Souiai,Claudia Nieuwenhuis,Evgeny Strekalovskiy,Daniel Cremers
Issue Date:December 2013
pp. 9-14
In this paper we give a convex optimization approach for scene understanding. Since segmentation, object recognition and scene labeling strongly benefit from each other we propose to solve these tasks within a single convex optimization problem. In contras...
 
Proximity Priors for Variational Semantic Segmentation and Recognition
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Julia Bergbauer,Claudia Nieuwenhuis,Mohamed Souiai,Daniel Cremers
Issue Date:December 2013
pp. 15-21
In this paper, we introduce the concept of proximity priors into semantic segmentation in order to discourage the presence of certain object classes (such as 'sheep' and 'wolf') 'in the vicinity' of each other. 'Vicinity' encompasses spatial distance as we...
 
Semi-dense Visual Odometry for a Monocular Camera
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Jakob Engel,Jurgen Sturm,Daniel Cremers
Issue Date:December 2013
pp. 1449-1456
We propose a fundamentally novel approach to real-time visual odometry for a monocular camera. It allows to benefit from the simplicity and accuracy of dense tracking - which does not depend on visual features - while running in real-time on a CPU. The key...
 
Proportion Priors for Image Sequence Segmentation
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Claudia Nieuwenhuis,Evgeny Strekalovskiy,Daniel Cremers
Issue Date:December 2013
pp. 2328-2335
We propose a convex multilabel framework for image sequence segmentation which allows to impose proportion priors on object parts in order to preserve their size ratios across multiple images. The key idea is that for strongly deformable objects such as a ...
 
Total Variation Regularization for Functions with Values in a Manifold
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Jan Lellmann,Evgeny Strekalovskiy,Sabrina Koetter,Daniel Cremers
Issue Date:December 2013
pp. 2944-2951
While total variation is among the most popular regularizers for variational problems, its extension to functions with values in a manifold is an open problem. In this paper, we propose the first algorithm to solve such problems which applies to arbitrary ...
 
Tree Shape Priors with Connectivity Constraints Using Convex Relaxation on General Graphs
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Jan Stuhmer,Peter Schroder,Daniel Cremers
Issue Date:December 2013
pp. 2336-2343
In this work we propose a novel method to include a connectivity prior into image segmentation that is based on a binary labeling of a directed graph, in this case a geodesic shortest path tree. Specifically we make two contributions: First, we construct a...
 
Large-Scale Multi-resolution Surface Reconstruction from RGB-D Sequences
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Frank Steinbrucker,Christian Kerl,Daniel Cremers
Issue Date:December 2013
pp. 3264-3271
We propose a method to generate highly detailed, textured 3D models of large environments from RGB-D sequences. Our system runs in real-time on a standard desktop PC with a state-of-the-art graphics card. To reduce the memory consumption, we fuse the acqui...
 
Elastic Net Constraints for Shape Matching
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Emanuele Rodola,Andrea Torsello,Tatsuya Harada,Yasuo Kuniyoshi,Daniel Cremers
Issue Date:December 2013
pp. 1169-1176
We consider a parametrized relaxation of the widely adopted quadratic assignment problem (QAP) formulation for minimum distortion correspondence between deformable shapes. In order to control the accuracy/sparsity trade-off we introduce a weighting paramet...
 
Introducing total curvature for image processing
Found in: Computer Vision, IEEE International Conference on
By Bastian Goldluecke,Daniel Cremers
Issue Date:November 2011
pp. 1267-1274
We introduce the novel continuous regularizer total curvature (TC) for images $\math$. It is defined as the Menger-Melnikov curvature of the Radon measure |Du|, which can be understood as a measure theoretic formulation of curvature mathematically related ...
 
Generalized ordering constraints for multilabel optimization
Found in: Computer Vision, IEEE International Conference on
By Evgeny Strekalovskiy,Daniel Cremers
Issue Date:November 2011
pp. 2619-2626
We propose a novel framework for imposing label ordering constraints in multilabel optimization. In particular, label jumps can be penalized differently depending on the jump direction. In contrast to the recently proposed MRF-based approaches, the propose...
 
A convex framework for image segmentation with moment constraints
Found in: Computer Vision, IEEE International Conference on
By Maria Klodt,Daniel Cremers
Issue Date:November 2011
pp. 2236-2243
Convex relaxation techniques have become a popular approach to image segmentation as they allow to compute solutions independent of initialization to a variety of image segmentation problems. In this paper, we will show that shape priors in terms of moment...
 
Tight convex relaxations for vector-valued labeling problems
Found in: Computer Vision, IEEE International Conference on
By Evgeny Strekalovskiy,Bastian Goldluecke,Daniel Cremers
Issue Date:November 2011
pp. 2328-2335
The multi-label problem is of fundamental importance to computer vision, yet finding global minima of the associated energies is very hard and usually impossible in practice. Recently, progress has been made using continuous formulations of the multi-label...
 
Geometrically consistent elastic matching of 3D shapes: A linear programming solution
Found in: Computer Vision, IEEE International Conference on
By Thomas Windheuser,Ulrich Schlickewei,Frank R. Schmidt,Daniel Cremers
Issue Date:November 2011
pp. 2134-2141
We propose a novel method for computing a geometrically consistent and spatially dense matching between two 3D shapes. Rather than mapping points to points we match infinitesimal surface patches while preserving the geometric structures. In this spirit we ...
 
Decoupling photometry and geometry in dense variational camera calibration
Found in: Computer Vision, IEEE International Conference on
By Mathieu Aubry,Kalin Kolev,Bastian Goldluecke,Daniel Cremers
Issue Date:November 2011
pp. 1411-1418
We introduce a spatially dense variational approach to estimate the calibration of multiple cameras in the context of 3D reconstruction. We propose a relaxation scheme which allows to transform the original photometric error into a geometric one, thereby d...
 
Fast Joint Estimation of Silhouettes and Dense 3D Geometry from Multiple Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kalin Kolev,Thomas Brox,Daniel Cremers
Issue Date:March 2012
pp. 493-505
We propose a probabilistic formulation of joint silhouette extraction and 3D reconstruction given a series of calibrated 2D images. Instead of segmenting each image separately in order to construct a 3D surface consistent with the estimated silhouettes, we...
 
Multiview Stereo and Silhouette Consistency via Convex Functionals over Convex Domains
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Daniel Cremers, Kalin Kolev
Issue Date:June 2011
pp. 1161-1174
We propose a convex formulation for silhouette and stereo fusion in 3D reconstruction from multiple images. The key idea is to show that the reconstruction problem can be cast as one of minimizing a convex functional, where the exact silhouette consistency...
 
An approach to vectorial total variation based on geometric measure theory
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Bastian Goldluecke, Daniel Cremers
Issue Date:June 2010
pp. 327-333
We analyze a previously unexplored generalization of the scalar total variation to vector-valued functions, which is motivated by geometric measure theory. A complete mathematical characterization is given, which proves important invariance properties as w...
 
A Combinatorial Solution for Model-Based Image Segmentation and Real-Time Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Thomas Schoenemann, Daniel Cremers
Issue Date:July 2010
pp. 1153-1164
We propose a combinatorial solution to determine the optimal elastic matching of a deformable template to an image. The central idea is to cast the optimal matching of each template point to a corresponding image pixel as a problem of finding a minimum cos...
 
Combined Region and Motion-Based 3D Tracking of Rigid and Articulated Objects
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Thomas Brox, Bodo Rosenhahn, Juergen Gall, Daniel Cremers
Issue Date:March 2010
pp. 402-415
In this paper, we propose the combined use of complementary concepts for 3D tracking: region fitting on one side and dense optical flow as well as tracked SIFT features on the other. Both concepts are chosen such that they can compensate for the shortcomin...
 
Fast and exact solution of Total Variation models on the GPU
Found in: Computer Vision and Pattern Recognition Workshop
By Thomas Pock, Markus Unger, Daniel Cremers, Horst Bischof
Issue Date:June 2008
pp. 1-8
This paper discusses fast and accurate methods to solve Total Variation (TV) models on the graphics processing unit (GPU). We review two prominent models incorporating TV regularization and present different algorithms to solve these models. We mainly conc...
 
Matching non-rigidly deformable shapes across images: A globally optimal solution
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Thomas Schoenemann, Daniel Cremers
Issue Date:June 2008
pp. 1-6
While global methods for matching shapes to images have recently been proposed, so far research has focused on small deformations of a fixed template.
 
High resolution motion layer decomposition using dual-space graph cuts
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Thomas Schoenemann, Daniel Cremers
Issue Date:June 2008
pp. 1-7
We introduce a novel energy minimization method to decompose a video into a set of super-resolved moving layers. The proposed energy corresponds to the cost of coding the sequence. It consists of a data term and two terms imposing regularity of the geometr...
 
Markerless motion capture of man-machine interaction
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Bodo Rosenhahn, Christian Schmaltz, Thomas Brox, Joachim Weickert, Daniel Cremers, Hans-Peter Seidel
Issue Date:June 2008
pp. 1-8
This work deals with modeling and markerless tracking of athletes interacting with sports gear. In contrast to classical markerless tracking, the interaction with sports gear comes along with joint movement restrictions due to additional constraints: while...
 
Shape priors in variational image segmentation: Convexity, Lipschitz continuity and globally optimal solutions
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Daniel Cremers, Frank R. Schmidt, Frank Barthel
Issue Date:June 2008
pp. 1-6
In this work, we introduce a novel implicit representation of shape which is based on assigning to each pixel a probability that this pixel is inside the shape. This probabilistic representation of shape resolves two important drawbacks of alternative impl...
 
Globally optimal shape-based tracking in real-time
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Thomas Schoenemann, Daniel Cremers
Issue Date:June 2008
pp. 1-6
Most algorithms for real-time tracking of deformable shapes provide sub-optimal solutions for a suitable energy minimization task: The search space is typically considered too large to allow for globally optimal solutions.
 
Fast Matching of Planar Shapes in Sub-cubic Runtime
Found in: Computer Vision, IEEE International Conference on
By Frank R. Schmidt, Dirk Farin, Daniel Cremers
Issue Date:October 2007
pp. 1-6
The matching of planar shapes can be cast as a problem of finding the shortest path through a graph spanned by the two shapes, where the nodes of the graph encode the local similarity of respective points on each contour. While this problem can be solved u...
 
Introducing Curvature into Globally Optimal Image Segmentation: Minimum Ratio Cycles on Product Graphs
Found in: Computer Vision, IEEE International Conference on
By Thomas Schoenemann, Daniel Cremers
Issue Date:October 2007
pp. 1-6
While the majority of competitive image segmentation methods are based on energy minimization, only few allow to efficiently determine globally optimal solutions. A graph-theoretic algorithm for finding globally optimal segmentations is given by the Minimu...
 
Globally Optimal Image Segmentation with an Elastic Shape Prior
Found in: Computer Vision, IEEE International Conference on
By Thomas Schoenemann, Daniel Cremers
Issue Date:October 2007
pp. 1-6
So far global optimization techniques have been developed independently for the tasks of shape matching and image segmentation. In this paper we show that both tasks can in fact be solved simultaneously using global optimization. By computing cycles of min...
 
Nonlinear Dynamical Shape Priors for Level Set Segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Daniel Cremers
Issue Date:June 2007
pp. 1-7
The introduction of statistical shape knowledge into level set based segmentation methods was shown to improve the segmentation of familiar structures in the presence of noise, clutter or partial occlusions. While most work has been focused on shape priors...
 
Shedding Light on Stereoscopic Segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hailin Jin, Daniel Cremers, Anthony J. Yezzi, Stefano Soatto
Issue Date:July 2004
pp. 36-42
We propose a variational algorithm to jointly estimate the shape, albedo, and light configuration of a Lambertian scene from a collection of images taken from different vantage points. Our work can be thought of as extending classical multi-view stereo to ...
 
Binary Partitioning, Perceptual Grouping, and Restoration with Semidefinite Programming
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jens Keuchel, Christoph Schnörr, Christian Schellewald, Daniel Cremers
Issue Date:November 2003
pp. 1364-1379
<p><b>Abstract</b>—We introduce a novel optimization method based on semidefinite programming relaxations to the field of computer vision and apply it to the combinatorial problem of minimizing quadratic functionals in binary decision var...
 
Dynamic Texture Segmentation
Found in: Computer Vision, IEEE International Conference on
By Gianfranco Doretto, Daniel Cremers, Paolo Favaro, Stefano Soatto
Issue Date:October 2003
pp. 1236
We address the problem of segmenting a sequence of images of natural scenes into disjoint regions that are characterized by constant spatio-temporal statistics. We model the spatio-temporal dynamics in each region by Gauss-Markov models, and infer the mode...
 
Variational Space-Time Motion Segmentation
Found in: Computer Vision, IEEE International Conference on
By Daniel Cremers, Stefano Soatto
Issue Date:October 2003
pp. 886
We propose a variational method for segmenting image sequences into spatio-temporal domains of homogeneous motion. To this end, we formulate the problem of motion estimation in the framework of Bayesian inference, using a prior which favors domain boundari...
 
A Variational Framework for Image Segmentation Combining Motion Estimation and Shape Regularization
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Daniel Cremers
Issue Date:June 2003
pp. 53
Based on a geometric interpretation of the optic flow constraint equation, we propose a conditional probability on the spatio-temporal image gradient. We consistently derive a variational approach for the segmentation of the image domain into regions of ho...
 
Diffusion-Snakes: Combining Statistical Shape Knowledge and Image Information in a Variational Framework
Found in: Variational and Level Set Methods in Computer Vision, IEEE Workshop on
By Daniel Cremers, Christoph Schnorr, Joachim Weickert
Issue Date:July 2001
pp. 137
We present a modification of the Mumford-Shah functional and its cartoon limit which allows the incorporation of statistical shape knowledge in a single energy functional. We show segmentation results on artificial and real-world images with and without pr...
 
Fast and Accurate Large-Scale Stereo Reconstruction Using Variational Methods
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Georg Kuschk,Daniel Cremers
Issue Date:December 2013
pp. 700-707
This paper presents a fast algorithm for high-accuracy large-scale outdoor dense stereo reconstruction of man-made environments. To this end, we propose a structure-adaptive second-order Total Generalized Variation (TGV) regularization which facilitates th...
 
Relative Volume Constraints for Single View 3D Reconstruction
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Eno Toppe,Claudia Nieuwenhuis,Daniel Cremers
Issue Date:June 2013
pp. 177-184
We introduce the concept of relative volume constraints in order to account for insufficient information in the reconstruction of 3D objects from a single image. The key idea is to formulate a variational reconstruction approach with shape priors in form o...
 
GPU histogram computation
Found in: ACM SIGGRAPH 2006 Research posters (SIGGRAPH '06)
By Daniel Cremers, Mikael Rousson, Oliver Fluck, Shmuel Aharon
Issue Date:July 2006
pp. 53-es
Visual Shaditor is a platform independent tool for developing complex vertex and fragment shaders. The results can be compiled directly as Cg or GLSL programs. The shaded 3D scene will be rendered and displayed immediately in a preview window. The system m...
     
GPU histogram computation
Found in: Material presented at the ACM SIGGRAPH 2006 conference (SIGGRAPH '06)
By Daniel Cremers, Mikael Rousson, Oliver Fluck, Shmuel Aharon
Issue Date:July 2006
pp. 53-es
Visual Shaditor is a platform independent tool for developing complex vertex and fragment shaders. The results can be compiled directly as Cg or GLSL programs. The shaded 3D scene will be rendered and displayed immediately in a preview window. The system m...
     
 1