Deep learning algorithms that rely on extensive training data are revolutionizing image recovery from ill-posed measurements. Training data is scarce in many imaging applications, including ultra-high-resolution imaging. The deep image prior (DIP) algorithm was introduced for single-shot image recovery, completely eliminating the need for training data. A challenge with this scheme is the need for early stopping to minimize the overfitting of the CNN parameters to the noise in the measurements. We introduce a generalized Stein's unbiased risk estimate (GSURE) loss metric to minimize the overfitting. Our experiments show that the SURE-DIP approach minimizes the overfitting issues, thus offering significantly improved performance over classical DIP schemes. We also use the SURE-DIP approach with model-based unrolling architectures, which offers improved performance over direct inversion schemes.
@article{arxiv.2111.10892,
title = {Deep Image Prior using Stein's Unbiased Risk Estimator: SURE-DIP},
author = {Maneesh John and Hemant Kumar Aggarwal and Qing Zou and Mathews Jacob},
journal= {arXiv preprint arXiv:2111.10892},
year = {2021}
}