DEEP VIDEO COMPRESSION FOR INTERFRAME CODING

被引：4

作者：

Alexandre, David ^{[1
]}

Hang, Hsueh-Ming ^{[1
]}

Peng, Wen-Hsiao ^{[1
]}

Domanski, Marek ^{[2
]}

机构：

[1] Natl Yang Ming Chiao Tung Univ, Taipei, Taiwan

[2] Poznan Univ Tech, Poznan, Poland

来源：

2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2021年

关键词：

Deep learning; video compression; predictive coding; video extrapolation;

D O I：

10.1109/ICIP42928.2021.9506275

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A typical learning-based video compression scheme consists of motion coding and residual coding. In this paper, our deep video compression features a motion predictor and refinement networks for interframe coding. To save the bits for transmitting motion information, our scheme performs local motion prediction and sends only the differential motion vectors to the decoder. In the residual coding, we couple the residual decoder with the refine-net to reduce residual signal bits. The experiments show that our work can produce a very competitive coding performance compared to the other learning-based predictive video codecs.

引用

页码：2124 / 2128

页数：5

共 17 条

[1]

Alexandre D., 2020, ARXIV201207462

[2]

Balle Johannes, 2018, arXiv preprint arXiv:1802.01436

[3] Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules [J].

Cheng, Zhengxue ;

Sun, Heming ;

Takeuchi, Masaru ;

Katto, Jiro .

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, :7936-7945

[4]

Duda Jarek, 2013, arXiv preprint arXiv:1311.2540

[5] Improving Deep Video Compression by Resolution-Adaptive Flow Coding [J].

Hu, Zhihao ;

Chen, Zhenghao ;

Xu, Dong ;

Lu, Guo ;

Ouyang, Wanli ;

Gu, Shuhang .

COMPUTER VISION - ECCV 2020, PT II, 2020, 12347 :193-209

[6] M-LVC: Multiple Frames Prediction for Learned Video Compression [J].

Lin, Jianping ;

Liu, Dong ;

Li, Houqiang ;

Wu, Feng .

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, :3543-3551

[7]

Lu G., 2020, P IEEE T PATT AN MAC

[8]

Lu G, 2019, IEEE ANTENNAS PROP, P1001, DOI [10.1109/APUSNCURSINRSM.2019.8888697, 10.1109/apusncursinrsm.2019.8888697]

[9] UVG Dataset: 50/120fps 4K Sequences for Video Codec Analysis and Development [J].

Mercat, Alexandre ;

Viitanen, Marko ;

Vanne, Jarno .

MMSYS'20: PROCEEDINGS OF THE 2020 MULTIMEDIA SYSTEMS CONFERENCE, 2020, :297-302

[10]

Minnen D, 2018, ADV NEUR IN, V31

← 1 2 →