Self-supervised fine-tuning for image enhancement of super-resolution deep neural networks

Alice Lucas, Santiago Lopez-Tapia, Rafael Molina, Aggelos K. Katsaggelos

Research output: Contribution to journalArticlepeer-review


While Deep Neural Networks (DNNs) trained for image and video super-resolution regularly achieve new state-of-the-art performance, they also suffer from significant drawbacks. One of their limitations is their tendency to generate strong artifacts in their solution. This may occur when the low-resolution image formation model does not match that seen during training. Artifacts also regularly arise when training Generative Adversarial Networks for inverse imaging problems. In this paper, we propose an efficient, fully self-supervised approach to remove the observed artifacts. More specifically, at test time, given an image and its known image formation model, we fine-tune the parameters of the trained network and iteratively update them using a data consistency loss. We apply our method to image and video super-resolution neural networks and show that our proposed framework consistently enhances the solution originally provided by the neural network.

Original languageEnglish (US)
JournalUnknown Journal
StatePublished - Dec 30 2019

ASJC Scopus subject areas

  • General

Fingerprint Dive into the research topics of 'Self-supervised fine-tuning for image enhancement of super-resolution deep neural networks'. Together they form a unique fingerprint.

Cite this