End-to-End Learnt Image Compression via Non-Local Attention Optimization and Improved Context Modeling

Tong Chen, Haojie Liu, Zhan Ma, Qiu Shen, Xun Cao, Yao Wang

Research output: Contribution to journalArticlepeer-review


This article proposes an end-to-end learnt lossy image compression approach, which is built on top of the deep nerual network (DNN)-based variational auto-encoder (VAE) structure with Non-Local Attention optimization and Improved Context modeling (NLAIC). Our NLAIC 1) embeds non-local network operations as non-linear transforms in both main and hyper coders for deriving respective latent features and hyperpriors by exploiting both local and global correlations, 2) applies attention mechanism to generate implicit masks that are used to weigh the features for adaptive bit allocation, and 3) implements the improved conditional entropy modeling of latent features using joint 3D convolutional neural network (CNN)-based autoregressive contexts and hyperpriors. Towards the practical application, additional enhancements are also introduced to speed up the computational processing (e.g., parallel 3D CNN-based context prediction), decrease the memory consumption (e.g., sparse non-local processing) and reduce the implementation complexity (e.g., a unified model for variable rates without re-training). The proposed model outperforms existing learnt and conventional (e.g., BPG, JPEG2000, JPEG) image compression methods, on both Kodak and Tecnick datasets with the state-of-the-art compression efficiency, for both PSNR and MS-SSIM quality measurements. We have made all materials publicly accessible at https://njuvision.github.io/NIC for reproducible research.

Original languageEnglish (US)
Article number9359473
Pages (from-to)3179-3191
Number of pages13
JournalIEEE Transactions on Image Processing
StatePublished - 2021


  • Learnt image compression
  • attention mechanism
  • conditional probability prediction
  • non-local network
  • variable-rate model

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'End-to-End Learnt Image Compression via Non-Local Attention Optimization and Improved Context Modeling'. Together they form a unique fingerprint.

Cite this