Name
Abstract | ||
|---|---|---|
Deep image priors (DIP) offer a novel approach for the regularization that leverages the inductive bias of a deep convolutional architecture in inverse problems. However, the quality of DIP approaches often degrades when the number of iterations exceeds a certain threshold due to overfitting. To mitigate this effect, this work incorporates a plug-and-play prior scheme which can accommodate additional regularization steps within a DIP framework. Our modification is achieved using an augmented Lagrangian formulation of the problem, and is solved using an Alternating Direction Method of Multipliers (ADMM) variant, which can capture existing DIP approaches as a special case. We show experimentally that our ADMM-based DIP pairing outperforms competitive baselines in PSNR while exhibiting less overfitting. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/ICASSP39728.2021.9414879 | 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) |
Keywords | DocType | Citations |
Deep Image Prior, Plug-and-Play Prior, Alternating Direction Method of Multipliers (ADMM), Inverse Problem, Overfitting | Conference | 0 |
PageRank | References | Authors |
0.34 | 9 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhaodong Sun | 1 | 0 | 0.34 |
| Fabian Latorre | 2 | 0 | 1.35 |
| Thomas Sanchez | 3 | 0 | 0.68 |
| Volkan Cevher | 4 | 6 | 1.77 |