The paper proposes a novel block-wise prediction paradigm based on Convolutional Neural Networks (CNN) for lossless video coding. A deep neural network model which follows a multi-resolution design is employed for block-wise prediction. A set of novel contributions is proposed to improve the neural network training. A first contribution proposes a novel loss function formulation for an efficient network training based on a new approach for patch selection. Another contribution consists in replacing all HEVC-based angular intra-prediction modes with a CNN-based intra-prediction method, where each angular prediction mode is complemented by a CNN-based prediction mode using a specifically trained model. Another contribution consists in an efficient adaptation of the CNN-based intra-prediction residual for lossless video coding. Experimental results on standard test sequences show that the proposed coding system outperforms the HEVC standard with an average bitrate improvement of around 5%. To our knowledge, the paper is the first to replace all the traditional HEVC-based angular intra-prediction modes with an intra-prediction method based on modern Machine Learning techniques.
Schiopu, I, Huang, H & Munteanu, A 2019, 'CNN-based Intra-Prediction for Lossless HEVC', IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 7, 8827579, pp. 1816 - 1828. https://doi.org/10.1109/TCSVT.2019.2940092
Schiopu, I., Huang, H., & Munteanu, A. (2019). CNN-based Intra-Prediction for Lossless HEVC. IEEE Transactions on Circuits and Systems for Video Technology, 30(7), 1816 - 1828. Article 8827579. https://doi.org/10.1109/TCSVT.2019.2940092
@article{7a7809df2930422f97e4bed6b56c3f94,
title = "CNN-based Intra-Prediction for Lossless HEVC",
abstract = "The paper proposes a novel block-wise prediction paradigm based on Convolutional Neural Networks (CNN) for lossless video coding. A deep neural network model which follows a multi-resolution design is employed for block-wise prediction. A set of novel contributions is proposed to improve the neural network training. A first contribution proposes a novel loss function formulation for an efficient network training based on a new approach for patch selection. Another contribution consists in replacing all HEVC-based angular intra-prediction modes with a CNN-based intra-prediction method, where each angular prediction mode is complemented by a CNN-based prediction mode using a specifically trained model. Another contribution consists in an efficient adaptation of the CNN-based intra-prediction residual for lossless video coding. Experimental results on standard test sequences show that the proposed coding system outperforms the HEVC standard with an average bitrate improvement of around 5%. To our knowledge, the paper is the first to replace all the traditional HEVC-based angular intra-prediction modes with an intra-prediction method based on modern Machine Learning techniques.",
keywords = "lossless video coding, Deep-learning, intra-prediction",
author = "Ionut Schiopu and Hongyue Huang and Adrian Munteanu",
year = "2019",
doi = "10.1109/TCSVT.2019.2940092",
language = "English",
volume = "30",
pages = "1816 -- 1828",
journal = "IEEE Transactions on Circuits and Systems for Video Technology",
issn = "1051-8215",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "7",
}