Image Deconvolution with Deep Image and Kernel Priors
This work addresses image deconvolution for computer vision applications, but it is incremental as it builds on existing deep image prior methods.
The authors tackled the ill-posed problem of image deconvolution by developing a model with deep image and kernel priors (DIKP), which improved performance on a standard benchmark of six test images in terms of PSNR and visual effects.
Image deconvolution is the process of recovering convolutional degraded images, which is always a hard inverse problem because of its mathematically ill-posed property. On the success of the recently proposed deep image prior (DIP), we build an image deconvolution model with deep image and kernel priors (DIKP). DIP is a learning-free representation which uses neural net structures to express image prior information, and it showed great success in many energy-based models, e.g. denoising, super-resolution, inpainting. Instead, our DIKP model uses such priors in image deconvolution to model not only images but also kernels, combining the ideas of traditional learning-free deconvolution methods with neural nets. In this paper, we show that DIKP improve the performance of learning-free image deconvolution, and we experimentally demonstrate this on the standard benchmark of six standard test images in terms of PSNR and visual effects.