Two-Layer Learning-based P-Frame Coding with Super-Resolution and Content-Adaptive Conditional ANF

被引:0
作者
Alexandre, David [1 ]
Hang, Hsueh-Ming [2 ]
Peng, Wen-Hsiao [3 ]
机构
[1] Natl Yang Ming Chiao Tung Univ, Dept Elect & Comp Engr, Hsinchu, Taiwan
[2] Natl Yang Ming Chiao Tung Univ, Dept Elect Engr, Hsinchu, Taiwan
[3] Natl Yang Ming Chiao Tung Univ, Dept Comp Sci, Hsinchu, Taiwan
来源
PROCEEDINGS OF THE 4TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA IN ASIA, MMASIA 2022 | 2022年
关键词
video compression; deep video coding; two-layer coding; skip mode coding; merge-net;
D O I
10.1145/3551626.3564953
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Deep-learning-based video compression technique has been rapidly growing in recent years. This paper adopts the Conditional Augmented Normalizing Flow video codec (CANF-VC) [8] as our basic system. To improve the quality of the condition signal (image) for CANF, we propose a two-layer structure learning-based video codec. At low cost of extra bit rate, the low-resolution base layer provides side information to improve the quality of motion-compensated reference frame through a super-resolution module with a merge-net. In addition, the base layer also provides information to the skip-mask generator. The skip-mask guides the coding mechanism to reduce the transmitted samples for the high-resolution enhancement layer. The experiment results indicate that the proposed two-layer coding scheme can provide 22.19% PSNR BD-Rate saving and 49.59% MS-SSIM BD-Rate saving over H.265 (HM 16.20) on the UVG test sequences.
引用
收藏
页数:7
相关论文
共 22 条
[1]  
Balle J., 2017, PROC INT C LEARN REP
[2]  
Balle Johannes, 2018, PROC INT C LEARN REP
[3]  
Bjontegaard Gisle, 2001, Tech. Rep. VCEG-M33
[4]  
Bossen F., 2013, JCTVC-L1100, V12
[5]  
Cheng ZX, 2020, PROC CVPR IEEE, P7936, DOI 10.1109/CVPR42600.2020.00796
[6]   CANF-VC: Conditional Augmented Normalizing Flows for Video Compression [J].
Ho, Yung-Han ;
Chang, Chih-Peng ;
Chen, Peng-Yu ;
Gnutti, Alessandro ;
Peng, Wen-Hsiao .
COMPUTER VISION - ECCV 2022, PT XVI, 2022, 13676 :207-223
[7]   ANFIC: Image Compression Using Augmented Normalizing Flows [J].
Ho, Yung-Han ;
Chan, Chih-Chun ;
Peng, Wen-Hsiao ;
Hang, Hsueh-Ming ;
Domanski, Marek .
IEEE OPEN JOURNAL OF CIRCUITS AND SYSTEMS, 2021, 2 :613-626
[8]   FVC: A New Framework towards Deep Video Compression in Feature Space [J].
Hu, Zhihao ;
Lu, Guo ;
Xu, Dong .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :1502-1511
[9]  
Joint Video Experts Team (JVET), 2018, Hevc Software Repository
[10]  
Li JH, 2021, ADV NEUR IN, V34