Deep Image Prior using Stein's Unbiased Risk Estimator: SURE-DIP
This addresses the challenge of early stopping to minimize noise overfitting in imaging applications where training data is scarce, such as ultra-high-resolution imaging, offering an incremental improvement over existing DIP methods.
The paper tackles the problem of overfitting in deep image prior (DIP) algorithms for single-shot image recovery without training data by introducing a generalized Stein's unbiased risk estimate (GSURE) loss metric, resulting in significantly improved performance over classical DIP schemes.
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.