Adversarial Regularizers in Inverse Problems
This addresses the problem of improving reconstruction quality in inverse problems for fields like medical imaging and computer vision, offering a novel data-driven approach that works with unsupervised training data, though it appears incremental as it builds on existing variational regularization models.
The paper tackles the challenge of solving inverse problems in medical imaging and computer vision by proposing a framework that uses a neural network as a regularization functional, learning from unsupervised data to discriminate between ground truth and unregularized reconstructions, with experiments showing potential for denoising on the BSDS dataset and computed tomography reconstruction on the LIDC dataset.
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 network as a regularization functional. The network learns to discriminate between the distribution of ground truth images and the distribution of unregularized reconstructions. Once trained, the network is applied to the inverse problem by solving the corresponding variational problem. Unlike other data-based approaches for inverse problems, the algorithm can be applied even if only unsupervised training data is available. Experiments demonstrate the potential of the framework for denoising on the BSDS dataset and for computed tomography reconstruction on the LIDC dataset.