JingyunLiang / MANet

Official PyTorch code for Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution (MANet, ICCV2021)

Home Page:https://arxiv.org/abs/2108.05302

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

[Can estimated kernels(spatially variant) be used to deconvolution debluring?]

CaptainEven opened this issue · comments

commented

Can estimated kernels(spatially variant) be applied to deconvolution debluring explicitly, using FFT and wiener filter?

It is possible, but I didn't try it. Note that for deconvolution, the kernels are often much more complex (e.g., motion blur). It may be harder to estimate the kernels accurately, though one good thing is that there is no downscaling in deconvolution. We can summarize them as follows:

image super-resolution: downscaling (hard, much loss of information) + blur (often assumed to be simple, at most anisotropic Gaussian) + noise

image deblurring: blur only (often motion blur kernels, as Gaussian blurs are too easy for this task, even traditional methods may solve it well) + noise

commented

@JingyunLiang Thanks for the explanation! I got it, and i 'll try it maybe when i'm free .

ezoic increase your site revenue