Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Yanchen, Duan, Wenhong, Jia, Chuanmin, Wang, Shanshe, Ma, Siwei
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2411.15759
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909403178860544
author Zhao, Yanchen
Duan, Wenhong
Jia, Chuanmin
Wang, Shanshe
Ma, Siwei
author_facet Zhao, Yanchen
Duan, Wenhong
Jia, Chuanmin
Wang, Shanshe
Ma, Siwei
contents In the fourth generation Audio Video coding Standard (AVS4), the Inter Prediction Filter (INTERPF) reduces discontinuities between prediction and adjacent reconstructed pixels in inter prediction. The paper proposes a low complexity learning-based inter prediction (LLIP) method to replace the traditional INTERPF. LLIP enhances the filtering process by leveraging a lightweight neural network model, where parameters can be exported for efficient inference. Specifically, we extract pixels and coordinates utilized by the traditional INTERPF to form the training dataset. Subsequently, we export the weights and biases of the trained neural network model and implement the inference process without any third-party dependency, enabling seamless integration into video codec without relying on Libtorch, thus achieving faster inference speed. Ultimately, we replace the traditional handcraft filtering parameters in INTERPF with the learned optimal filtering parameters. This practical solution makes the combination of deep learning encoding tools with traditional video encoding schemes more efficient. Experimental results show that our approach achieves 0.01%, 0.31%, and 0.25% coding gain for the Y, U, and V components under the random access (RA) configuration on average.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15759
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Advanced Learning-Based Inter Prediction for Future Video Coding
Zhao, Yanchen
Duan, Wenhong
Jia, Chuanmin
Wang, Shanshe
Ma, Siwei
Multimedia
Computer Vision and Pattern Recognition
In the fourth generation Audio Video coding Standard (AVS4), the Inter Prediction Filter (INTERPF) reduces discontinuities between prediction and adjacent reconstructed pixels in inter prediction. The paper proposes a low complexity learning-based inter prediction (LLIP) method to replace the traditional INTERPF. LLIP enhances the filtering process by leveraging a lightweight neural network model, where parameters can be exported for efficient inference. Specifically, we extract pixels and coordinates utilized by the traditional INTERPF to form the training dataset. Subsequently, we export the weights and biases of the trained neural network model and implement the inference process without any third-party dependency, enabling seamless integration into video codec without relying on Libtorch, thus achieving faster inference speed. Ultimately, we replace the traditional handcraft filtering parameters in INTERPF with the learned optimal filtering parameters. This practical solution makes the combination of deep learning encoding tools with traditional video encoding schemes more efficient. Experimental results show that our approach achieves 0.01%, 0.31%, and 0.25% coding gain for the Y, U, and V components under the random access (RA) configuration on average.
title Advanced Learning-Based Inter Prediction for Future Video Coding
topic Multimedia
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.15759