Regularization of inverse visual problems involving discontinuities
IEEE Transactions on Pattern Analysis and Machine Intelligence
Visual reconstruction
Computational framework for determining stereo correspondence from a set of linear spatial filters
Image and Vision Computing - Special issue: 2nd European Conference on Computer Vision
Three-dimensional computer vision: a geometric viewpoint
Three-dimensional computer vision: a geometric viewpoint
A Bayesian approach to binocular stereopsis
International Journal of Computer Vision
Stereo Without Epipolar Lines: A Maximum-Flow Formulation
International Journal of Computer Vision - Special issue on computer vision research at NEC Research Institute
Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Bayesian Modeling of Uncertainty in Low-Level Vision
Bayesian Modeling of Uncertainty in Low-Level Vision
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
International Journal of Computer Vision
Occlusions, Discontinuities, and Epipolar Lines in Stereo
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Stereo Matching Using Belief Propagation
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Maximum-Flow Formulation of the N-Camera Stereo Correspondence Problem
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Comparison of Graph Cuts with Belief Propagation for Stereo, using Identical MRF Parameters
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Rethinking the prior model for stereo
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
Exact optimization for Markov random fields with convex priors
IEEE Transactions on Pattern Analysis and Machine Intelligence
An Unbiased Second-Order Prior for High-Accuracy Motion Estimation
Proceedings of the 30th DAGM symposium on Pattern Recognition
| Hi-index | 0.00 |
In spite of the great progress in stereo matching algorithms, the prior models they use, i.e., the assumptions about the probability to see each possible surface, have not changed much in three decades. Here, we introduce a novel prior model motivated by psychophysical experiments. It is based on minimizing the total sum of the absolute value of the Gaussian curvature over the disparity surface. Intuitively, it is similar to rolling and bending a flexible paper to fit to the stereo surface, whereas the conventional prior is more akin to spanning a soap film. Through controlled experiments, we show that the new prior outperforms the conventional models, when compared in the equal setting.