Logo image
Back
Deep Image Prior using Stein's Unbiased Risk Estimator: SURE-DIP
Preprint   Open access

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

Maneesh John, Hemant Kumar Aggarwal, Qing Zou and Mathews Jacob
ArXiv.org
11/21/2021
DOI: 10.48550/arXiv.2111.10892
url
https://arxiv.org/abs/2111.10892View
Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

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.

Details

Metrics

28 Record Views
Logo image