Ozan Öktem — accepted AI-conference papers

2024

Data-Driven Convex Regularizers for Inverse Problems

Subhadip Mukherjee, Sören Dittmer, Zakhar Shumaylov, Sebastian Lunz, Ozan Öktem, Carola B. Schönlieb

ICASSP 2024accepted

We propose to learn a data-adaptive convex regularizer, which is parameterized using an input-convex neural network (ICNN), for variational image reconstruction. The regularizer parameters are learned adversarially by telling apart clean images from the artifact-ridden ones in a training dataset. Co…

Cited by 0 Source ↗Scholar ↗

2021

End-to-end reconstruction meets data-driven regularization for inverse problems

Subhadip Mukherjee, Marcello Carioni, Ozan Öktem, Carola-Bibiane Schönlieb

NeurIPS 2021poster

We propose a new approach for learning end-to-end reconstruction operators based on unpaired training data for ill-posed inverse problems. The proposed method combines the classical variational framework with iterative unrolling and essentially seeks to minimize a weighted combination of the expecte…

Cited by 46 Source ↗PDF ↗code ↗Scholar ↗

2018

Adversarial Regularizers in Inverse Problems

Sebastian Lunz, Ozan Öktem, Carola-Bibiane Schönlieb

NeurIPS 2018poster

Inverse Problems in medical imaging and computer vision are traditionally solved using purely model-based methods. Among those variational regularization models are one of the most popular approaches. We propose a new framework for applying data-driven approaches to inverse problems, using a neural…

Cited by 298 Source ↗PDF ↗code ↗Scholar ↗