Optic flow goes stereo: a variational method for estimating discontinuity-preserving dense disparity maps

Authors:
Natalia Slesareva;Andrés Bruhn;Joachim Weickert
Affiliations:
Mathematical Image Analysis Group, Faculty of Mathematics and Computer Science, Saarland University, Saarbrücken, Germany;Mathematical Image Analysis Group, Faculty of Mathematics and Computer Science, Saarland University, Saarbrücken, Germany;Mathematical Image Analysis Group, Faculty of Mathematics and Computer Science, Saarland University, Saarbrücken, Germany
Venue:
PR'05 Proceedings of the 27th DAGM conference on Pattern Recognition
Year:
2005

Citing 11
Cited 14

Nonlinear total variation based noise removal algorithms

Proceedings of the eleventh annual international conference of the Center for Nonlinear Studies on Experimental mathematics : computational issues in nonlinear science: computational issues in nonlinear science
Three-dimensional computer vision: a geometric viewpoint

Three-dimensional computer vision: a geometric viewpoint
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
Real-Time Correlation-Based Stereo Vision with Reduced Border Errors

International Journal of Computer Vision
Dense Depth Map Reconstruction: A Minimization and Regularization Approach which Preserves Discontinuities

ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Optimization of Stereo Disparity Estimation Using the Instantaneous Frequency

CAIP '97 Proceedings of the 7th International Conference on Computer Analysis of Images and Patterns
Disparity from Monogenic Phase

Proceedings of the 24th DAGM Symposium on Pattern Recognition
Stereo Matching with Non-Linear Diffusion

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Regularizing Phase-Based Stereo

ICPR '96 Proceedings of the 1996 International Conference on Pattern Recognition (ICPR '96) Volume I - Volume 7270
Multi-Camera Real-Time Depth Estimation with Discontinuity Handling on PC Graphics Hardware

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
Computational Experiments with a Feature Based Stereo Algorithm

IEEE Transactions on Pattern Analysis and Machine Intelligence

A Geometric Approach for Regularization of the Data Term in Stereo-Vision

Journal of Mathematical Imaging and 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
Hyperbolic Numerics for Variational Approaches to Correspondence Problems

SSVM '09 Proceedings of the Second International Conference on Scale Space and Variational Methods in Computer Vision
A convex optimization approach for depth estimation under illumination variation

IEEE Transactions on Image Processing
Simultaneous estimation of surface motion, depth and slopes under changing illumination

Proceedings of the 29th DAGM conference on Pattern recognition
Depth MAP compression VIA compressed sensing

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Stereo depth estimation using synchronous optimization with segment based regularization

Pattern Recognition Letters
Real-time dense geometry from a handheld camera

Proceedings of the 32nd DAGM conference on Pattern recognition
Can Variational Models for Correspondence Problems Benefit from Upwind Discretisations?

Journal of Mathematical Imaging and Vision
Dense versus Sparse Approaches for Estimating the Fundamental Matrix

International Journal of Computer Vision
Over-Parameterized optical flow using a stereoscopic constraint

SSVM'11 Proceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision
Error concealment by means of motion refinement and regularized bregman divergence

IDEAL'12 Proceedings of the 13th international conference on Intelligent Data Engineering and Automated Learning
An interactive system for set reconstruction from multiple input sources

Proceedings of the Symposium on Digital Production
3D Scene Reconstruction from Multiple Spherical Stereo Pairs

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel variational method for estimating dense disparity maps from stereo images. It integrates the epipolar constraint into the currently most accurate optic flow method (Brox et al. 2004). In this way, a new approach is obtained that offers several advantages compared to existing variational methods: (i) It preservers discontinuities very well due to the use of the total variation as solution-driven regulariser. (ii) It performs favourably under noise since it uses a robust function to penalise deviations from the data constraints. (iii) Its minimisation via a coarse-to-fine strategy can be theoretically justified. Experiments with both synthetic and real-world data show the excellent performance and the noise robustness of our approach.