In the research literature, maximum likelihood principles were applied to stereo matching by altering the stereo pair so that the difference would have a Gaussian distribution. Here in this paper we present a novel method of applying maximum likelihood to stereo matching. In our approach, we measure the real noise distribution from a training set, and then construct a new metric which we denote the maximum likelihood metric for comparing the stereo pair. The maximum likelihood metric is optimal in the sense that it maximizes the probability of similarity. In our experiments and discussion, we compared the maximum likelihood metric to other promising algorithms from the research literature using international stereo data sets. Furthermore, w...
This paper presents a quantitative evaluation of two area-based stereo matching approaches aimed at ...
We propose a new approach to associate supervised learning-based confidence prediction with the ster...
Under the popular Bayesian approach, a stereo problem can be formulated by defining likelihood and p...
The Euclidean metric is frequently used in Computer Vision, mostly ad-hoc without any justification....
AbstractÐImage matching applications such as tracking and stereo commonly use the sum-of-squared-dif...
The aim of stereo matching is to find a corresponding point for each pixel in a reference image of a...
In this paper we present a new method for matching stereo\ud image pairs. This technique is based on...
Mutual information (MI) has shown promise as an effective stereo matching measure for images affecte...
We introduce a new likelihood function for window-based stereo matching. This likelihood can cope wi...
One of the central problems in stereo matching (and other image registration tasks) is the selection...
Abstract. Brute-force dense matching is usually not satisfactory because the same search range is us...
Abstract — This paper introduces a novel non-parametric sta-tistical metric that can decide if the r...
Abstract. One of the central problems in stereo matching (and other image registration tasks) is the...
The authors present a qualitative and quantitative comparison of various similarity measures that fo...
The authors present a qualitative and quantitative comparison of various similarity measures that fo...
This paper presents a quantitative evaluation of two area-based stereo matching approaches aimed at ...
We propose a new approach to associate supervised learning-based confidence prediction with the ster...
Under the popular Bayesian approach, a stereo problem can be formulated by defining likelihood and p...
The Euclidean metric is frequently used in Computer Vision, mostly ad-hoc without any justification....
AbstractÐImage matching applications such as tracking and stereo commonly use the sum-of-squared-dif...
The aim of stereo matching is to find a corresponding point for each pixel in a reference image of a...
In this paper we present a new method for matching stereo\ud image pairs. This technique is based on...
Mutual information (MI) has shown promise as an effective stereo matching measure for images affecte...
We introduce a new likelihood function for window-based stereo matching. This likelihood can cope wi...
One of the central problems in stereo matching (and other image registration tasks) is the selection...
Abstract. Brute-force dense matching is usually not satisfactory because the same search range is us...
Abstract — This paper introduces a novel non-parametric sta-tistical metric that can decide if the r...
Abstract. One of the central problems in stereo matching (and other image registration tasks) is the...
The authors present a qualitative and quantitative comparison of various similarity measures that fo...
The authors present a qualitative and quantitative comparison of various similarity measures that fo...
This paper presents a quantitative evaluation of two area-based stereo matching approaches aimed at ...
We propose a new approach to associate supervised learning-based confidence prediction with the ster...
Under the popular Bayesian approach, a stereo problem can be formulated by defining likelihood and p...