This work introduces the multiframe motion-compensation enhancement network (MMCE-Net), a deep-learning tool aimed at improving the performance of current video coding standards based on motion-compensation, such as H.265/HEVC. The proposed method improves the inter-prediction coding efficiency by enhancing the accuracy of the motion-compensated frame and thereby improving the rate-distortion performance. MMCE-Net is a neural network that jointly exploits the predicted coding unit and two co-located coding units from previous reference frames to improve the estimation of the temporal evolution of the scene. This letter describes the architecture of MMCE-Net, how it is integrated into H.265/HEVC and the corresponding performance.

Deep motion‐compensation enhancement in video compression / Prette, Nicola; Valsesia, Diego; Bianchi, Tiziano; Magli, Enrico; Naccari, Matteo; Fiandrotti, Attilio. - In: ELECTRONICS LETTERS. - ISSN 0013-5194. - ELETTRONICO. - (2022). [10.1049/ell2.12475]

Deep motion‐compensation enhancement in video compression

Prette, Nicola;Valsesia, Diego;Bianchi, Tiziano;Magli, Enrico;
2022

Abstract

This work introduces the multiframe motion-compensation enhancement network (MMCE-Net), a deep-learning tool aimed at improving the performance of current video coding standards based on motion-compensation, such as H.265/HEVC. The proposed method improves the inter-prediction coding efficiency by enhancing the accuracy of the motion-compensated frame and thereby improving the rate-distortion performance. MMCE-Net is a neural network that jointly exploits the predicted coding unit and two co-located coding units from previous reference frames to improve the estimation of the temporal evolution of the scene. This letter describes the architecture of MMCE-Net, how it is integrated into H.265/HEVC and the corresponding performance.
2022
File in questo prodotto:
File Dimensione Formato  
Electronics Letters - 2022 - Prette - Deep motion‐compensation enhancement in video compression.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Creative commons
Dimensione 699.72 kB
Formato Adobe PDF
699.72 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

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/11583/2960843