Scalable Learned Image Compression with A Recurrent Neural Networks-Based Hyperprior

Rige Su, Zhengxue Cheng, Heming Sun, Jiro Katto

研究成果: Conference contribution

抄録

Recently learned image compression has achieved many great progresses, such as representative hyperprior and its variants based on convolutional neural networks (CNNs). However, CNNs are not fit for scalable coding and multiple models need to be trained separately to achieve variable rates. In this paper, we incorporate differentiable quantization and accurate entropy models into recurrent neural networks (RNNs) architectures to achieve a scalable learned image compression. First, we present an RNN architecture with quantization and entropy coding. To realize the scalable coding, we allocate the bits to multiple layers, by adjusting the layer-wise lambda values in Lagrangian multiplier-based rate-distortion optimization function. Second, we add an RNN-based hyperprior to improve the accuracy of entropy models for multiple-layer residual representations. Experimental results demonstrate that our performance can be comparable with recent CNN-based hyperprior methods on Kodak dataset. Besides, our method is a scalable and flexible coding approach, to achieve multiple rates using one single model, which is very appealing.

本文言語English
ホスト出版物のタイトル2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings
出版社IEEE Computer Society
ページ3369-3373
ページ数5
ISBN(電子版)9781728163956
DOI
出版ステータスPublished - 2020 10
イベント2020 IEEE International Conference on Image Processing, ICIP 2020 - Virtual, Abu Dhabi, United Arab Emirates
継続期間: 2020 9 252020 9 28

出版物シリーズ

名前Proceedings - International Conference on Image Processing, ICIP
2020-October
ISSN(印刷版)1522-4880

Conference

Conference2020 IEEE International Conference on Image Processing, ICIP 2020
CountryUnited Arab Emirates
CityVirtual, Abu Dhabi
Period20/9/2520/9/28

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

フィンガープリント 「Scalable Learned Image Compression with A Recurrent Neural Networks-Based Hyperprior」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル