Video restoration with a deep plug-and-play prior.
Saved in:
| Title: | Video restoration with a deep plug-and-play prior. |
|---|---|
| Authors: | Monod, Antoine1,2 (AUTHOR) amonod@gopro.com, Delon, Julie1 (AUTHOR) julie.delon@u-paris.fr, Almansa, Andrés1 (AUTHOR) andres.almansa@u-paris.fr, Coupeté, Eva2 (AUTHOR) eva.coupete@gmail.com, Tassano, Matias3 (AUTHOR) tasso.matias@gmail.com |
| Source: | EURASIP Journal on Image & Video Processing. 3/19/2026, Vol. 2026 Issue 1, p1-24. 24p. |
| Subjects: | Embedded computer systems, Deep learning, High resolution imaging, Image denoising, Interpolation, Algorithms, Image enhancement (Imaging systems) |
| Abstract: | Performing video restoration in embedded systems is a challenge. Indeed, state-of-the-art learning-based methods in video restoration are specifically trained for given tasks, and often rely on huge networks, which makes them unsuitable when memory and computing resources are limited. In this paper, we explore the use of deep Plug-and-Play (PnP) algorithms for video restoration. We distinguish ourselves from prior PnP work by directly writing PnP schemes on video sequences instead of separate images. Our experiments in video deblurring, super-resolution (SR), and pixel interpolation all show a clear benefit to using a network specifically designed for video denoising, as it yields better restoration performance than a single image network with similar denoising performance using the same PnP formulation, and more temporal stability than other image-based PnP works. Experiments also highlight that, while not always as effective as state-of-the-art single-task deep networks, our lightweight approach remains competitive for many video restoration tasks. [ABSTRACT FROM AUTHOR] |
| Copyright of EURASIP Journal on Image & Video Processing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Performing video restoration in embedded systems is a challenge. Indeed, state-of-the-art learning-based methods in video restoration are specifically trained for given tasks, and often rely on huge networks, which makes them unsuitable when memory and computing resources are limited. In this paper, we explore the use of deep Plug-and-Play (PnP) algorithms for video restoration. We distinguish ourselves from prior PnP work by directly writing PnP schemes on video sequences instead of separate images. Our experiments in video deblurring, super-resolution (SR), and pixel interpolation all show a clear benefit to using a network specifically designed for video denoising, as it yields better restoration performance than a single image network with similar denoising performance using the same PnP formulation, and more temporal stability than other image-based PnP works. Experiments also highlight that, while not always as effective as state-of-the-art single-task deep networks, our lightweight approach remains competitive for many video restoration tasks. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 16875176 |
| DOI: | 10.1186/s13640-025-00669-0 |
