Download
DeconvDemo is a Qt & opencv based image deconvolution/ deblur software which is including the spatial and frequency domain solver.
image deconvolution / deblur software
with non-blind deconvolution algorithm
New:
Add pregressive non-blined deconvolution
Add blind kernel estimation
Implemented mehtod:
METHOD_WIENER,
METHOD_TIKHONOV,
METHOD_LUCY_RICHARDSON,
METHOD_CONJUGATE_GRADIENT,
METHOD_SPARSE_PRIOR,
METHOD_GAUSSIAN_PRIOR,
METHOD_NAIVE_EDGE_ENHANCEMENT,
METHOD_CONVOLUTION,
METHOD_PROGRESSIVE,
METHOD_BLIND_KERNEL
Improving:
sparse prior blind deconvolution.
PS: Please feel free to ask me any question and report bugs.
Project Samples
Categories
Digital CameraFollow DeconvDemo
Other Useful Business Software
Enterprise-grade ITSM, for every business
Freshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
Rate This Project
Login To Rate This Project
User Reviews
-
It seems to me an interesting software, although it falls short for its use in my hobby: astrophotography. It would be much better if it supported TIFF image format; the PSF image should support at least one decimal place for all three parameters; there is little control over the result, since it would be necessary to be able to control the number of standard deviations of the Gaussian blur, a parameter that controls the mix between the sharp and blurred areas, and a factor that allows smoothing the effect of each iteration if necessary.
-
My equation is totally the same with WIKI. en.wikipedia.org/wiki/Wiener_deconvolution Note that the number are complex numbers.
-
Dear adahbingee, I tested your soft last week, the results on my personal images & psf with the Wiener filter are very impressive. Thanks to your soft I know Wiener filter is the right filter to use for my needs. So I tried to code my own wiener filter with OpenCV/C++, but I can't get the same results: My original image is improved, but nothing compared with your soft. Did you use a special version of the filter ? I used the formula described in Wikipedia. What is the "smooth" slide in your GUI ? Is it the noise/signal ratio ? Thanks for your answers ! Andre