Blind image deconvolution (BID) is a severely ill-posed optimization problem and the quality of its solution depends on additional information, typically in the form of regularization. Deep image prior promises to model a naturally looking image due to a well-chosen structure of a neural network. The use of deep priors in BID results in significant performance improvement in terms of average PSNR. The focus of this seminar will be on an explanation of the benefits of DIP in BID and the analysis of other aspects of DIP-based BID algorithms (initialization, optimization method and regularization by traditional sharp-image priors). Their behavior will be studied on the solution with artifacts and the no-blur solution with the help of a metric distinguishing these two undesired solutions.