Real-World Video Restoration using Noise2Noise

Martin Zach, Erich Kobler

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review


Restoration of real-world analog video is a challenging task due to the presence of very heterogeneous defects. These defects are hard to model, such that creating training data synthetically is infeasible and instead time-consuming manual editing is required. In this work we explore whether reasonable restoration models can be learned from data without explicitly modeling the defects or manual editing. We adopt Noise2Noise techniques, which eliminate the need for ground truth targets by replacing them with corrupted instances. To compensate for temporal mismatches between the frames and ensure meaningful training, we apply motion correction. Our experiments show that video restoration can be learned using only corrupted frames, with performance exceeding that of conventional learning.
Original languageEnglish
Title of host publicationJoint Austrian Computer Vision and Robotics Workshop 2020
PublisherVerlag der Technischen Universität Graz
Number of pages5
ISBN (Electronic)978-3-85125-752-6
Publication statusPublished - 2020
EventJoint Austrian Computer Vision and Robotics Workshop 2020 - Technische Universität Graz, abgesagt, Austria
Duration: 17 Sep 202018 Sep 2020


ConferenceJoint Austrian Computer Vision and Robotics Workshop 2020
Abbreviated titleACVRW 20


Dive into the research topics of 'Real-World Video Restoration using Noise2Noise'. Together they form a unique fingerprint.

Cite this