Motion estimation and motion compensation are indispensable parts of inter prediction in video coding. Since the motion vector of objects is mostly in fractional pixel units, original reference pictures may not accurately provide a suitable reference for motion compensation. In this paper, we propose a deep reference picture generator which can create a picture that is more relevant to the current encoding frame, thereby further reducing temporal redundancy and improving video compression efficiency. Inspired by the recent progress of Convolutional Neural Network(CNN), this paper proposes to use a dilated CNN to build the generator. Moreover, we insert the generated deep picture into Versatile Video Coding(VVC) as a reference picture and perform a comprehensive set of experiments to evaluate the effectiveness of our network on the latest VVC Test Model-VTM. The experimental results demonstrate that our proposed method achieves on average 9.7% bit saving compared with VVC under low-delay P configuration.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing
Subtitle of host publicationProceedings
Place of PublicationUnited States
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages5
ISBN (Electronic)9781665405409
ISBN (Print)9781665405416 (Print on demand)
Publication statusE-pub ahead of print - 27 Apr 2022
Event47th IEEE International Conference on Acoustics, Speech, and Signal Processing: ICASSP 2022 - Marina Bay Sands Expo & Convention Center, Singapore, Singapore
Duration: 23 May 202227 May 2022
https://2022.ieeeicassp.org/ (Conference website)

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149


Conference47th IEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated titleHuman-centric signal processing
OtherThe International Conference on Acoustics, Speech, & Signal Processing (ICASSP), is the IEEE Signal Processing Society’s flagship conference on signal processing and its applications. The 47th edition of ICASSP will be held in Singapore. The programme will include keynotes by pre-eminent international speakers, cutting-edge tutorial topics, and forward-looking special sessions. ICASSP also provides a great networking opportunity with a wide range of like-minded professionals from academia.
Internet address


Dive into the research topics of 'Dilated convolutional neural network-based deep reference picture generation for video compression'. Together they form a unique fingerprint.

Cite this