Image Deblurring via Extreme Channels Prior
Citations
213 citations
Cites methods from "Image Deblurring via Extreme Channe..."
...Several recent methods introduce new image priors that favor clear images over blurred ones in the MAP framework [20, 45, 30, 33, 46]....
[...]
194 citations
184 citations
Cites background or methods from "Image Deblurring via Extreme Channe..."
..., l1/l2-norm [15], patchbased prior [24, 41], low-rank prior [34] and dark channel prior [29, 50] have also been proposed to identify and preserve salient edges for benefiting blur kernel estimation....
[...]
...Under the MAP-based framework, many fixed and handcrafted regularization terms have been presented for latent clean image and blur kernel [22, 24, 29, 29, 34, 41, 50, 56]....
[...]
...Although many priors have been suggested for x [2, 15, 27, 56] and k [19, 22, 24, 29, 29, 34, 41, 50, 56], they generally are handcrafted and certainly are insufficient in characterizing clean images and blur kernels....
[...]
132 citations
Cites background or methods or result from "Image Deblurring via Extreme Channe..."
...Our method generates a more visually pleasing result against [27, 28], and contain less ringing artifacts than dark channel based method[20]....
[...]
...Kernel estimated by extreme channel prior[28] result in large residual blur, and the result generated by our model compares favorably with the method tailored to text [19]....
[...]
...Recent approaches enforce sparsity on the dark channel [20] and the bright channel [28] of latent images....
[...]
...(15) with FFT (Fast Fourier Transform) directly, and the solution can be obtained according to [27, 28]....
[...]
...A number of image priors have also been utilized to solve this ill-posed problem [16, 11, 21, 20, 28, 15]....
[...]
128 citations
Cites background from "Image Deblurring via Extreme Channe..."
...jointly estimate a transmission map and the underlying hazefree image via designing clear image priors [40], [41]....
[...]
References
1,919 citations
"Image Deblurring via Extreme Channe..." refers background or methods in this paper
...Figure 5(a) indicates that our ECP based algorithm performs well against the state-of-the-art methods [2, 5, 19, 12, 16, 25] on this benchmark dataset [13] in terms of cumulative error ratio....
[...]
...We evaluate the performance of the proposed approach against the state-of-the-art methods [13, 2, 5, 19, 12, 16, 25]....
[...]
...Such as heavy-tailed gradient distributions [5, 13], normalized sparsity prior [12], L0-regularized gradient [25], patch recurrence prior [15], and a combination of the intensity and gradient prior [16]....
[...]
1,338 citations
1,279 citations
"Image Deblurring via Extreme Channe..." refers methods in this paper
...We further validate our observation with the statistics of the bright channels by randomly selecting 5000 images from the PASCAL 2012 dataset [1] without any manually pre-processing....
[...]
1,220 citations
"Image Deblurring via Extreme Channe..." refers methods in this paper
...To estimate blur kernels from blurry images, other existing approaches utilize statistical priors[4, 20, 14, 12, 25, 16] or additional information [8, 3, 9] to solve the ill-posed problem....
[...]
1,219 citations
"Image Deblurring via Extreme Channe..." refers background or methods in this paper
...In addition, we also show the performances of the proposed algorithm against the DCP-based [17] and BCPbased methods on this benchmark dataset [13] in terms of the cumulative error ratio....
[...]
...Such as heavy-tailed gradient distributions [5, 13], normalized sparsity prior [12], L0-regularized gradient [25], patch recurrence prior [15], and a combination of the intensity and gradient prior [16]....
[...]
...To better verify the effectiveness of our proposed method, we use the image benchmark datasets [13, 11] for quantitative evaluations and follow the protocols of [13, 11] for fair comparisons....
[...]
...Quantitative evaluations on the benchmark datasets by [13] and [11], respectively....
[...]
...Quantitative evaluations on the benchmark dataset by [13] with and without using DCP or BCP....
[...]