Resolution Enhancement in Multi-Image Stereo
Citations
4 citations
Cites background from "Resolution Enhancement in Multi-Ima..."
...Super Resolution is the process of combining multiple noisy, blurry, low resolution images into a high quality, high resolution image....
[...]
4 citations
4 citations
Cites background from "Resolution Enhancement in Multi-Ima..."
...Note that the works on depth pixel reconstruction can be found in [20]–[22]....
[...]
3 citations
3 citations
References
7,458 citations
7,413 citations
"Resolution Enhancement in Multi-Ima..." refers background or methods in this paper
...If the scene mainly consists of discontinuous depth planes, we choose a Potts model [ 2 ] (equivalent to choosing T as the minimum depth label)....
[...]
...The minimization for depth is carried out by � -expansion graph cuts [ 2 ] and that for the image is carried out using iterated conditional modes (ICM) [6], [33]....
[...]
...Graph cuts is one of the better performing contemporary algorithms for stereo disparity estimation and we too employ it. Its advantage is its efficiency and the guarantee of reaching a strong local minimum [ 2 ]....
[...]
2,556 citations
"Resolution Enhancement in Multi-Ima..." refers methods in this paper
...For the multiview temple scene, where we compute the depth map (instead of disparity), the depth step was computed using the resolution information provided on the Middlebury multiview Web page [27]....
[...]
...Finally, we provide results for SR by 2 on the Middlebury multiview temple data set [27]....
[...]
...We carried out experiments on the Middlebury [26], [27], [35] and CMU data sets [34], as well as images captured in our lab....
[...]
1,334 citations
"Resolution Enhancement in Multi-Ima..." refers methods in this paper
...Many methods exist for handling visibility [4], [10], [14], [29], [31]....
[...]
1,333 citations
"Resolution Enhancement in Multi-Ima..." refers methods in this paper
...The termsEzðzÞ andExðxÞ correspond to the weighted MRF priors applied on the depth and the image, respectively....
[...]