A Hybrid Image Codec with Learned Residual Coding

被引:0
|
作者
Lee, Wei-Cheng [1 ]
Hang, Hsueh-Ming [1 ]
机构
[1] Natl Chiao Tung Univ, Dept Elect Engn, Hsinchu, Taiwan
关键词
D O I
10.1109/CVPRW50498.2020.00077
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a three-layer image compression system consisting of a base-layer VVC (intra) codec, a learning-based residual layer codec, and a learnable hyperprior. This proposal (Team: NCTU Commlab) is submitted to the Challenge on Learned Image Compression (CLIC) in March 2020. Our contribution is developing a data fusion attention module and integrating several known components together to form an efficient image codec, which has a higher compression performance than the standard VVC coding scheme. Unlike the conventional residual image coding, both our encoder and decoder take inputs also from the base-layer output. Also, we construct a refinement neural network to merge the residual-layer decoded residual image and the base-layer decoded image together to form the final reconstructed image. We tested two autoencoder structures for the encoder and decoder, namely, CNN with GDN [5, 6], and the generalized octave CNN [4]. Our results show that the transmitted latent representations are very efficient in coding the residuals because the object boundary information can be provided by the proposed spatial attention module. The experiments indicate that the proposed system achieves better performance than the single-layer VVC at both PSNR and subjective quality at around 0.15 bit-per-pixel.
引用
收藏
页码:570 / 574
页数:5
相关论文
共 50 条
  • [1] A hybrid transform coding for video codec
    Ezhilarasan, M.
    Thambidurai, P.
    [J]. ICIT 2006: 9TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY, PROCEEDINGS, 2006, : 117 - +
  • [2] IMPROVING RESIDUAL CODING OF WASP LIGHT FIELD CODEC
    Astola, Pekka
    Tabus, Ioan
    [J]. 2018 INTERNATIONAL CONFERENCE ON 3D IMMERSION (IC3D), 2018,
  • [3] Real-time Learned Image Codec on FPGA
    Sun, Heming
    Yi, Qingyang
    Lin, Fangzheng
    Yu, Lu
    Katto, Jiro
    Fujita, Masahiro
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP), 2022,
  • [4] SLIC: A Learned Image Codec Using Structure and Color
    Prativadibhayankaram, Srivatsa
    Panda, Mahadev Prasad
    Richter, Thomas
    Sparenberg, Heiko
    Foessel, Siegfried
    Kaup, Andre
    [J]. 2024 DATA COMPRESSION CONFERENCE, DCC, 2024, : 3 - 12
  • [5] A Multiple Description Video Codec With Adaptive Residual Distributed Coding
    Chen, Jiann-Jone
    Lee, Shih-Chieh
    Chen, Ching-Hua
    Sun, Chen-Hsiang
    Jhuang, Jyun-Jie
    Lu, Chi-Chun
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2012, 22 (05) : 754 - 768
  • [6] Green Image Codec: A Lightweight Learning-based Image Coding Method
    Wang, Yifan
    Mei, Zhanxuan
    Zhou, Qingyang
    Katsavounidis, Ioannis
    Kuo, C-C Jay
    [J]. APPLICATIONS OF DIGITAL IMAGE PROCESSING XLV, 2022, 12226
  • [7] Green Image Codec: A Lightweight Learning-based Image Coding Method
    Wang, Yifan
    Mei, Zhanxuan
    Zhou, Qingyang
    Katsavounidis, Ioannis
    Jay Kuo, C.-C.
    [J]. Proceedings of SPIE - The International Society for Optical Engineering, 2022, 12226
  • [8] Features Denoising for Learned Image Coding
    Mari, Daniele
    Milani, Simone
    [J]. 2022 10TH EUROPEAN WORKSHOP ON VISUAL INFORMATION PROCESSING (EUVIP), 2022,
  • [9] An efficient image codec based on backward coding of wavelet trees
    Guo, Jiangling
    Mitra, Sunanda
    Nutter, Brian
    Karp, Tanja
    [J]. 7TH IEEE SOUTHWEST SYMPOSIUM ON IMAGE ANALYSIS AND INTERPRETATION, 2006, : 233 - +
  • [10] Residual image coding for stereo image compression
    Frajka, T
    Zeger, K
    [J]. 2002 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL II, PROCEEDINGS, 2002, : 217 - 220