Video restoration techniques aim to remove artifacts, such as noise, blur, and compression, introduced at various levels within and outside the camera imaging pipeline during video acquisition. Although excellent results can be achieved by considering one artifact at a time, in real applications a given video sequence can be affected by multiple artifacts, whose appearance is mutually influenced. In this paper, we present Multi-distorted Video Restoration Network (MdVRNet), a deep neural network specifically designed to handle multiple distortions simultaneously. Our model includes an original Distortion Parameter Estimation sub-Network (DPEN) to automatically infer the intensity of various types of distortions affecting the input sequence, novel Multi-scale Restoration Blocks (MRB) to extract complementary features at different scales using two parallel streams, and implements a two-stage restoration process to focus on different levels of detail. We document the accuracy of the DPEN module in estimating the intensity of multiple distortions, and present an ablation study that quantifies the impact of the DPEN and MRB modules. Finally, we show the advantages of the proposed MdVRNet in a direct comparison with another existing state-of-the-art approach for video restoration.

Rota, C., Buzzelli, M. (2022). MdVRNet: Deep Video Restoration under Multiple Distortions. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - (Volume 4) (pp.419-426). AV D MANUELL, 27A 2 ESQ, SETUBAL, 2910-595, PORTUGAL : SCITEPRESS [10.5220/0010828900003124].

MdVRNet: Deep Video Restoration under Multiple Distortions

Rota, Claudio
;
Buzzelli, Marco
2022

Abstract

Video restoration techniques aim to remove artifacts, such as noise, blur, and compression, introduced at various levels within and outside the camera imaging pipeline during video acquisition. Although excellent results can be achieved by considering one artifact at a time, in real applications a given video sequence can be affected by multiple artifacts, whose appearance is mutually influenced. In this paper, we present Multi-distorted Video Restoration Network (MdVRNet), a deep neural network specifically designed to handle multiple distortions simultaneously. Our model includes an original Distortion Parameter Estimation sub-Network (DPEN) to automatically infer the intensity of various types of distortions affecting the input sequence, novel Multi-scale Restoration Blocks (MRB) to extract complementary features at different scales using two parallel streams, and implements a two-stage restoration process to focus on different levels of detail. We document the accuracy of the DPEN module in estimating the intensity of multiple distortions, and present an ablation study that quantifies the impact of the DPEN and MRB modules. Finally, we show the advantages of the proposed MdVRNet in a direct comparison with another existing state-of-the-art approach for video restoration.
No
paper
Video Restoration, Video Enhancement, Multiple Distortions, Denoising, Compression Artifacts;
English
17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP 2022) - FEB 06-08, 2022
978-989-758-555-5
https://www.scitepress.org/Link.aspx?doi=10.5220/0010828900003124
Rota, C., Buzzelli, M. (2022). MdVRNet: Deep Video Restoration under Multiple Distortions. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - (Volume 4) (pp.419-426). AV D MANUELL, 27A 2 ESQ, SETUBAL, 2910-595, PORTUGAL : SCITEPRESS [10.5220/0010828900003124].
Rota, C; Buzzelli, M
File in questo prodotto:
File Dimensione Formato  
VISAPP_2022_102_CR.pdf

Solo gestori archivio

Descrizione: Articolo principale
Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Dimensione 5.06 MB
Formato Adobe PDF
5.06 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/354150
Citazioni
  • Scopus ND
  • ???jsp.display-item.citation.isi??? 1
Social impact