This work proposes a novel Deep Learning technique to increase the efficiency of currently available video compression techniques based on motion compensation. The goal is to improve the frame prediction task, whereby a more accurate prediction of the motion from the reference frames to the target frame allows to reduce the rate needed to encode the residual. This is achieved by means of a convolutional neural network (CNN) architecture that processes the basic block-based motion-compensated prediction of the current frame as well as predictions from past reference frames. This method allows to reduce typical artifacts such as blockiness, and achieves a more accurate prediction of motion thanks to the representation capabilities of CNNs, leading to smaller prediction residuals. Preliminary results show that the proposed approach is capable of providing BD-rate gains up to 6%.
Deep Multiframe Enhancement for Motion Prediction in Video Compression / Prette, N.; Valsesia, D.; Bianchi, T.. - ELETTRONICO. - (2021), pp. 1-6. (Intervento presentato al convegno 28th IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2021 tenutosi a Dubai, United Arab Emirates nel 28 Nov.-1 Dec. 2021) [10.1109/ICECS53924.2021.9665523].
Deep Multiframe Enhancement for Motion Prediction in Video Compression
Prette N.;Valsesia D.;Bianchi T.
2021
Abstract
This work proposes a novel Deep Learning technique to increase the efficiency of currently available video compression techniques based on motion compensation. The goal is to improve the frame prediction task, whereby a more accurate prediction of the motion from the reference frames to the target frame allows to reduce the rate needed to encode the residual. This is achieved by means of a convolutional neural network (CNN) architecture that processes the basic block-based motion-compensated prediction of the current frame as well as predictions from past reference frames. This method allows to reduce typical artifacts such as blockiness, and achieves a more accurate prediction of motion thanks to the representation capabilities of CNNs, leading to smaller prediction residuals. Preliminary results show that the proposed approach is capable of providing BD-rate gains up to 6%.File | Dimensione | Formato | |
---|---|---|---|
Prette_ICECS22.pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
1.34 MB
Formato
Adobe PDF
|
1.34 MB | Adobe PDF | Visualizza/Apri |
Valsesia-DeepMultiframe.pdf
accesso riservato
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
3.78 MB
Formato
Adobe PDF
|
3.78 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2956158