@inproceedings{e8a177093ba241b19699d2e5c65f9756,
title = "Conditional Variational Autoencoders for Hierarchical B-frame Coding",
abstract = "In response to the Grand Challenge on Neural Network-based Video Coding at ISCAS 2024, this paper proposes a learned hierarchical B-frame coding scheme. Most learned video codecs concentrate on P-frame coding for the RGB content, while B-frame coding for the YUV420 content remains largely under-explored. Some early works explore Conditional Augmented Normalizing Flows (CANF) for B-frame coding. However, they suffer from high computational complexity because of stacking multiple variational autoencoders (VAE) and using separate Y and UV codecs. This work aims to develop a lightweight VAE-based B-frame codec in a conditional coding framework. It features (1) extracting multi-scale features for conditional motion and inter-frame coding, (2) performing frame-type adaptive coding for better bit allocation, and (3) a lightweight conditional VAE backbone that encodes YUV420 content by a simple conversion into YUV444 content for joint Y and UV coding. Experimental results confirms its superior compression performance to the CANF-based B-frame codec from the last year's challenge while having much reduced complexity.",
keywords = "B-frame coding, Learned video coding, YUV420",
author = "Gao, {Zong Lin} and Chen, {Cheng Wei} and Yao, {Yi Chen} and Ho, {Cheng Yuan} and Peng, {Wen Hsiao}",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2024 IEEE International Symposium on Circuits and Systems, ISCAS 2024 ; Conference date: 19-05-2024 Through 22-05-2024",
year = "2024",
doi = "10.1109/ISCAS58744.2024.10558111",
language = "English",
series = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "ISCAS 2024 - IEEE International Symposium on Circuits and Systems",
address = "美國",
}