TY - GEN
T1 - LEARNING-BASED VIDEO COMPRESSION WITH CONTINUOUSLY VARIABLE BITRATE CODING
AU - Yang, Mingyi
AU - Mao, Xionghui
AU - Yin, Yujie
AU - Zhu, Zhiwei
AU - Wang, Defa
AU - Wan, Shuai
AU - Yang, Fuzheng
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - In this paper, we propose a learning-based video compression which can perform continuously variable bitrate coding. The proposed method generates feature transformation parameters through a conditional network according to the input spatial quality map. These parameters are then used to adaptively transform the intermediate features of the encoder, decoder, and spatiotemporal entropy model in the codec, thus enabling variable bitrate coding. Additionally, to improve the compression efficiency of the codec, we propose incorporating the quality map of the preceding frame into the hyperprior encoder and leveraging the temporal prior encoder. A multi-stage training strategy is employed to jointly train the codec with a multi-frame rate-distortion loss function. The experimental results demonstrate that the proposed method can achieve continuously variable bitrate adaptation while maintaining rate-distortion performance comparable to the fixed bitrate model. Furthermore, the proposed method also supports ROI-based compression.
AB - In this paper, we propose a learning-based video compression which can perform continuously variable bitrate coding. The proposed method generates feature transformation parameters through a conditional network according to the input spatial quality map. These parameters are then used to adaptively transform the intermediate features of the encoder, decoder, and spatiotemporal entropy model in the codec, thus enabling variable bitrate coding. Additionally, to improve the compression efficiency of the codec, we propose incorporating the quality map of the preceding frame into the hyperprior encoder and leveraging the temporal prior encoder. A multi-stage training strategy is employed to jointly train the codec with a multi-frame rate-distortion loss function. The experimental results demonstrate that the proposed method can achieve continuously variable bitrate adaptation while maintaining rate-distortion performance comparable to the fixed bitrate model. Furthermore, the proposed method also supports ROI-based compression.
KW - Deep learning
KW - ROI-based compression
KW - Variable-rate compression
KW - Video compression
UR - http://www.scopus.com/inward/record.url?scp=85216868942&partnerID=8YFLogxK
U2 - 10.1109/ICIP51287.2024.10647741
DO - 10.1109/ICIP51287.2024.10647741
M3 - 会议稿件
AN - SCOPUS:85216868942
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 3723
EP - 3729
BT - 2024 IEEE International Conference on Image Processing, ICIP 2024 - Proceedings
PB - IEEE Computer Society
T2 - 31st IEEE International Conference on Image Processing, ICIP 2024
Y2 - 27 October 2024 through 30 October 2024
ER -