Recursive Video Matting and Denoising
References
5,314 citations
"Recursive Video Matting and Denoisi..." refers background in this paper
...Since (3) is non-linear, we resort to the UKF, which is based on the principle of unscented transformation (UT), to calculate moments of nonlinearly transformed random variable (see [9] and [14] for details)....
[...]
...where M = 4 is the dimension of augmented mean; λ = u(2)(M +κ)−M and κ = 2 are the scaling parameters, while u = 1 is the sigma point spread [9]....
[...]
...where α̂− is the predicted mean of α, ŷα is the weighted observation mean, and y is the given observed image (refer [9] for expressions of weights)....
[...]
2,902 citations
"Recursive Video Matting and Denoisi..." refers methods in this paper
...An accurate optical flow method presented in [6] (which is robust to reasonable levels of noise) is utilized for motion estimation, using the implementation given in [1]....
[...]
407 citations
"Recursive Video Matting and Denoisi..." refers methods in this paper
...An interactive cutout method that utilizes spatio-temporal coherence is described in [15], but it is not precise in cases of fine details or significant camera translation....
[...]
388 citations
"Recursive Video Matting and Denoisi..." refers background or methods or result in this paper
...where c denotes color plane and B is an arbitrary background [7]....
[...]
...The problem of video matting was first described in [7], which used a Bayesian technique to solve for α, F and B....
[...]
..., new features appear in future frames), we can combine both forward and backward flow, as described in [7]....
[...]
...Figure 2(a) (top row) shows an image taken from the video provided by [7], while the bottom row shows an image from a 1960’s video (with real film-grain) obtained from archives [2]....
[...]
...We have not compared with other still image matting methods, since only the Bayesian matting approach has been extended to video [7]....
[...]
350 citations
"Recursive Video Matting and Denoisi..." refers methods in this paper
...Segmentation of objects from dynamic backgrounds using Kalman filtering is proposed in [16]....
[...]