Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Leannec, Fabrice Le"'
A quantitative analysis of post-VVC luma and chroma intra tools is presented, focusing on their statistical behaviors, in terms of block selection rate under different conditions. The aim is to provide insights to the standardization community, offer
Externí odkaz:
http://arxiv.org/abs/2404.07872
Publikováno v:
VCIP 2021
This paper presents a learning-based method to improve bi-prediction in video coding. In conventional video coding solutions, the motion compensation of blocks from already decoded reference pictures stands out as the principal tool used to predict t
Externí odkaz:
http://arxiv.org/abs/2202.03149
Autor:
Galpin, Franck, Racapé, Fabien, Jaiswal, Sunil, Bordes, Philippe, Léannec, Fabrice Le, François, Edouard
Publikováno v:
2019 Data Compression Conference (DCC)
This paper provides a technical overview of a deep-learning-based encoder method aiming at optimizing next generation hybrid video encoders for driving the block partitioning in intra slices. An encoding approach based on Convolutional Neural Network
Externí odkaz:
http://arxiv.org/abs/2011.06691
Publikováno v:
2021 International Conference on Visual Communications and Image Processing (VCIP).
This paper presents a learning-based method to improve bi-prediction in video coding. In conventional video coding solutions, the motion compensation of blocks from already decoded reference pictures stands out as the principal tool used to predict t
Publikováno v:
2016 Data Compression Conference (DCC); 2016, p309-318, 10p
Publikováno v:
2016 Data Compression Conference (DCC); 2016, p628-628, 1p