Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
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.
Jean-Baptiste Francis Marie Juliette Cordonnier
Sabine Süsstrunk, Majed El Helou
Sabine Süsstrunk, Majed El Helou, Qiyuan Liang