Open MariasStory opened 5 years ago
Thanks for your suggestions. The current SelfDeblur works well for image deblurring with ideal convolution degradation model, but is still facing several issues: 1) high computational cost due to optimization of two networks; 2) not very robust to non-Gaussian noise and non-uniform blur. This paper is an attempt to address image deblurring using deep models, and we want to draw more research attention to address these issues together, leading to an effective and efficient image deblurring solution. I am preparing the code that will be released ASAP, and then you can directly sense the effectiveness and weakness of SelfDeblur. Thanks.
Hi @csdwren, thanks for the cool research and the open source. Do you plan to provide something like a (ideally - free) online image deblur solution? I imagine that it should be easy to setup. It would be also nice to pack complete solution, with model, for local image deblurring.