Deep Frame Prediction for Video Coding

We propose a novel frame prediction method using a deep neural network (DNN), with the goal of improving the video coding efficiency. The proposed DNN makes use of decoded frames, at both the encoder and decoder to predict the textures of the current coding block. Unlike conventional inter-predictio...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on circuits and systems for video technology Ročník 30; číslo 7; s. 1843 - 1855
Hlavní autoři: Choi, Hyomin, Bajic, Ivan V.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.07.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Artificial neural networks
Bidirectional control
Coders
Coding standards
deep learning
deep neural network (DNN)
Encoding
frame prediction
Interpolation
Neural networks
Random access
Tensors
texture prediction
Video coding
Video compression
ISSN:1051-8215, 1558-2205
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We propose a novel frame prediction method using a deep neural network (DNN), with the goal of improving the video coding efficiency. The proposed DNN makes use of decoded frames, at both the encoder and decoder to predict the textures of the current coding block. Unlike conventional inter-prediction, the proposed method does not require any motion information to be transferred between the encoder and the decoder. Still, both the uni-directional and bi-directional predictions are possible using the proposed DNN, which is enabled by the use of the temporal index channel, in addition to the color channels. In this paper, we developed a jointly trained DNN for both uni-directional and bi-directional predictions, as well as separate networks for uni-directional and bi-directional predictions, and compared the efficacy of both the approaches. The proposed DNNs were compared with the conventional motion-compensated prediction in the latest video coding standard, High Efficiency Video Coding (HEVC), in terms of the BD-bitrate. The experiments show that the proposed joint DNN (for both uni-directional and bi-directional predictions) reduces the luminance bitrate by about 4.4%, 2.4%, and 2.3% in the low delay <inline-formula> <tex-math notation="LaTeX">P </tex-math></inline-formula>, low delay, and random access configurations, respectively. In addition, using the separately trained DNNs brings further bit savings of about 0.3%-0.5%.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1051-8215
1558-2205
DOI:10.1109/TCSVT.2019.2924657