End-to-end optimized image compression with competition of prior distributions

被引:3
|
作者
Brummer, Benoit [1 ]
De Vleeschouwer, Christophe [2 ]
机构
[1] IntoPIX, Mont St Guibert, Belgium
[2] Catholic Univ Louvain, Louvain, Belgium
关键词
D O I
10.1109/CVPRW53098.2021.00212
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Convolutional autoencoders are now at the forefront of image compression research. To improve their entropy coding, encoder output is typically analyzed with a second autoencoder to generate per-variable parametrized prior probability distributions. We instead propose a compression scheme that uses a single convolutional autoencoder and multiple learned prior distributions working as a competition of experts. Trained prior distributions are stored in a static table of cumulative distribution functions. During inference, this table is used by an entropy coder as a look-up-table to determine the best prior for each spatial location. Our method offers rate-distortion performance comparable to that obtained with a predicted parametrized prior with only a fraction of its entropy coding and decoding complexity.
引用
收藏
页码:1890 / 1894
页数:5
相关论文
共 50 条
  • [31] NN-based Embedment of Watermark in End-to-end Image Compression
    Lee, EunSeong
    Lee, Jongseok
    Seo, Young-Ho
    Sim, Donggyu
    INTERNATIONAL WORKSHOP ON ADVANCED IMAGING TECHNOLOGY, IWAIT 2023, 2023, 12592
  • [32] TRELLIS-CODED QUANTIZATION FOR END-TO-END LEARNED IMAGE COMPRESSION
    Suhring, Karsten
    Schafer, Michael
    Pfaff, Jonathan
    Schwarz, Heiko
    Marpe, Detlev
    Wiegand, Thomas
    2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2022, : 3306 - 3310
  • [33] END-TO-END LEARNED IMAGE COMPRESSION WITH FIXED POINT WEIGHT QUANTIZATION
    Sun, Heming
    Cheng, Zhengxue
    Takeuchi, Masaru
    Katto, Jiro
    2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2020, : 3359 - 3363
  • [34] New Results in End-to-end Image and Video Compression by Deep Learning
    Ozsoy, Gokberk
    Yilmaz, Melih
    Kirmemis, Ogun
    Tekalp, A. Murat
    2020 28TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2020,
  • [35] End-to-End Facial Image Compression with Integrated Semantic Distortion Metric
    He, Tianyu
    Chen, Zhibo
    2018 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (IEEE VCIP), 2018,
  • [36] Image Compression Based on Compressive Sensing: End-to-End Comparison With JPEG
    Yuan, Xin
    Haimi-Cohen, Raziel
    IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 22 (11) : 2889 - 2904
  • [37] End-to-End Multispectral Image Compression Using Convolutional Neural Network
    Kong Fanqiang
    Zhou Yongbo
    Shen Qiu
    Wen Keyao
    CHINESE JOURNAL OF LASERS-ZHONGGUO JIGUANG, 2019, 46 (10):
  • [38] End-to-End Learning-Based Image Compression With a Decoupled Framework
    Zhang, Zhaobin
    Esenlik, Semih
    Wu, Yaojun
    Wang, Meng
    Zhang, Kai
    Zhang, Li
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (05) : 3067 - 3081
  • [39] CPIPS: Learning to Preserve Perceptual Distances in End-to-End Image Compression
    Huang, Chen-Hsiu
    Wu, Ja-Ling
    2023 ASIA PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE, APSIPA ASC, 2023, : 1705 - 1711
  • [40] TRANSFORM SKIP INSPIRED END-TO-END COMPRESSION FOR SCREEN CONTENT IMAGE
    Wang, Meng
    Zhang, Kai
    Zhang, Li
    Wu, Yaojun
    Li, Yue
    Li, Junru
    Wang, Shiqi
    2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2022, : 3848 - 3852