Deep Image Prior using Stein's Unbiased Risk Estimator: SURE-DIP

Understand

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.