@InProceedings{OliveiraMJGSSEHTF:2021:LeEnVi,
author = "Oliveira, Matheus Costa de and Martins, Luiz Gustavo Rodrigues and
Jung, Henrique Costa and Guerin Junior, Nilson Donizete and Silva,
Renam Castro da and Silva, Eduardo Peixoto Fernandes da and
Espinoza, Bruno Luiggi Macchiavello and Hung, Edson Mintsu and
Testoni, Vanessa and Freitas, Pedro Garcia",
affiliation = "{University of Bras{\'{\i}}lia } and {University of
Bras{\'{\i}}lia } and {University of Bras{\'{\i}}lia } and
{University of Bras{\'{\i}}lia } and {Samsung R\&D Brazil } and
{University of Bras{\'{\i}}lia } and {University of
Bras{\'{\i}}lia } and {University of Bras{\'{\i}}lia } and
{Samsung R\&D Brazil } and {Samsung R\&D Brazil}",
title = "Learning-based End-to-End Video Compression Using Predictive
Coding",
booktitle = "Proceedings...",
year = "2021",
editor = "Paiva, Afonso and Menotti, David and Baranoski, Gladimir V. G. and
Proen{\c{c}}a, Hugo Pedro and Junior, Antonio Lopes Apolinario
and Papa, Jo{\~a}o Paulo and Pagliosa, Paulo and dos Santos,
Thiago Oliveira and e S{\'a}, Asla Medeiros and da Silveira,
Thiago Lopes Trugillo and Brazil, Emilio Vital and Ponti, Moacir
A. and Fernandes, Leandro A. F. and Avila, Sandra",
organization = "Conference on Graphics, Patterns and Images, 34. (SIBGRAPI)",
publisher = "IEEE Computer Society",
address = "Los Alamitos",
keywords = "neural coding, video coding, intra prediction, inter prediction,
autoencoder.",
abstract = "Driven by the growing demand for video applications, deep learning
techniques have become alternatives for implementing end-to-end
encoders to achieve applicable compression rates. Conventional
video codecs exploit both spatial and temporal correlation.
However, due to some restrictions (e.g. computational complexity),
they are commonly limited to linear transformations and
translational motion estimation. Autoencoder models open up the
way for exploiting predictive end-to-end video codecs without such
limitations. This paper presents an entire learning-based video
codec that exploits spatial and temporal correlations. The
presented codec extends the idea of P-frame prediction presented
in our previous work. The architecture adopted for I-frame coding
is defined by a variational autoencoder with non-parametric
entropy modeling. Besides an entropy model parameterized by a
hyperprior, the inter-frame encoder architecture has two other
independent networks, responsible for motion estimation and
residue prediction. Experimental results indicate that some
improvements still have to be incorporated into our codec to
overcome the all-intra coding set up regarding the traditional
algorithms HEVC and VVC.",
conference-location = "Gramado, RS, Brazil (virtual)",
conference-year = "18-22 Oct. 2021",
doi = "10.1109/SIBGRAPI54419.2021.00030",
url = "http://dx.doi.org/10.1109/SIBGRAPI54419.2021.00030",
language = "en",
ibi = "8JMKD3MGPEW34M/45CG3KP",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45CG3KP",
targetfile = "Camera Ready Version - PDF eXpress.pdf",
urlaccessdate = "2024, May 06"
}