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.
@article{arxiv.1910.08386,
title = {Image Deconvolution with Deep Image and Kernel Priors},
author = {Zhunxuan Wang and Zipei Wang and Qiqi Li and Hakan Bilen},
journal= {arXiv preprint arXiv:1910.08386},
year = {2022}
}
Comments
In Proceedings of the 2019 IEEE International Conference on Computer Vision Workshops (ICCVW)