mlsanityData to 7 Oct 2026

Non-local Attention Optimized Deep Image Compression

arXiv 1904.09757 ↗First posted 22 Apr 2019eess.IV cs.CVcited by 86

Not on the map. Why?

Abstract (arXiv)

This paper proposes a novel Non-Local Attention Optimized Deep Image Compression (NLAIC) framework, which is built on top of the popular variational auto-encoder (VAE) structure. Our NLAIC framework embeds non-local operations in the encoders and decoders for both image and latent feature probability information (known as hyperprior) to capture both local and global correlations, and apply attention mechanism to generate masks that are used to weigh the features for the image and hyperprior, which implicitly adapt bit allocation for different features based on their importance. Furthermore, both hyperpriors and spatial-channel neighbors of the latent features are used to improve entropy coding. The proposed model outperforms the existing methods on Kodak dataset, including learned (e.g., Balle2019, Balle2018) and conventional (e.g., BPG, JPEG2000, JPEG) image compression methods, for both PSNR and MS-SSIM distortion metrics.

Key facts. Cited by 86 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 23; 2023: 20; 2024: 16; 2025: 11; 2026: 4.

86 papers.

Sort:

By area:

  1. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  2. 2022Entroformer: A Transformer-based Entropy Model for Learned Image Compressioncited by 102
  3. 2022MLIC: Multi-Reference Entropy Model for Learned Image Compressioncited by 80
  4. 2021Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compressioncited by 69
  5. 2021Transformer-based Image Compressioncited by 60
  6. 2023MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compressioncited by 56
  7. 2022CANF-VC: Conditional Augmented Normalizing Flows for Video Compressioncited by 44
  8. 2022Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compressioncited by 42
  9. 2023Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Triggercited by 40
  10. 2021Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modulescited by 33
  11. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 32
  12. 2021Extending Neural P-frame Codecs for B-frame Codingcited by 30
38 more
  1. 2022Neural Data-Dependent Transform for Learned Image Compressioncited by 29
  2. 2021Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuningcited by 24
  3. 2021ANFIC: Image Compression Using Augmented Normalizing Flowscited by 20
  4. 2025Learned Image Compression with Hierarchical Progressive Context Modelingcited by 20
  5. 2024Causal Context Adjustment Loss for Learned Image Compressioncited by 19
  6. 2022Preprocessing Enhanced Image Compression for Machine Visioncited by 18
  7. 2022Efficient Visual Computing with Camera RAW Snapshotscited by 18
  8. 2025Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusioncited by 17
  9. 2022High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregationcited by 16
  10. 2024Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Modelcited by 16
  11. 2022MobileCodec: Neural Inter-frame Video Compression on Mobile Devicescited by 15
  12. 2022Neural Distributed Image Compression with Cross-Attention Feature Alignmentcited by 15
  13. 2021CSformer: Bridging Convolution and Transformer for Compressive Sensingcited by 14
  14. 2023Multi-Modality Deep Network for Extreme Learned Image Compressioncited by 14
  15. 2022Learning-Driven Lossy Image Compression; A Comprehensive Surveycited by 13
  16. 2023Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compressioncited by 13
  17. 2021Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compressioncited by 12
  18. 2023FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computingcited by 12
  19. 2024When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Codingcited by 11
  20. 2024Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Priorcited by 11
  21. 2023Dynamic Low-Rank Instance Adaptation for Universal Neural Image Compressioncited by 10
  22. 2022High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformationcited by 8
  23. 2022Attention-Based Generative Neural Image Compression on Solar Dynamics Observatorycited by 8
  24. 2024Generalized Gaussian Model for Learned Image Compressioncited by 8
  25. 2021Rate Distortion Characteristic Modeling for Neural Image Compressioncited by 6
  26. 2021Universal Efficient Variable-rate Neural Image Compressioncited by 6
  27. 2022Learned Image Compression with Generalized Octave Convolution and Cross-Resolution Parameter Estimationcited by 6
  28. 2023Machine Perception-Driven Image Compression: A Layered Generative Approachcited by 6
  29. 2023LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compressioncited by 6
  30. 2023Multi-Context Dual Hyper-Prior Neural Image Compressioncited by 6
  31. 2022Estimating the Resize Parameter in End-to-end Learned Image Compressioncited by 5
  32. 2024DeepHQ: Learned Hierarchical Quantizer for Progressive Deep Image Codingcited by 5
  33. 2021Learning-Based Video Coding with Joint Deep Compression and Enhancementcited by 4
  34. 2022Exploring Structural Sparsity in Neural Image Compressioncited by 4
  35. 2022Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domaincited by 4
  36. 2024STanH : Parametric Quantization for Variable Rate Learned Image Compressioncited by 4
  37. 2025Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compressioncited by 4
  38. 2023Make Lossy Compression Meaningful for Low-Light Imagescited by 3

50 most cited of 86 All 86 (JSON)