mlsanityData to 7 Oct 2026

Joint Autoregressive and Hierarchical Priors for Learned Image Compression

arXiv 1809.02736 ↗First posted 8 Sep 2018cs.CVcited by 642

Not on the map. Why?

Cited by 41 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent models for learned image compression are based on autoencoders, learning approximately invertible mappings from pixels to a quantized latent representation. These are combined with an entropy model, a prior on the latent representation that can be used with standard arithmetic coding algorithms to yield a compressed bitstream. Recently, hierarchical entropy models have been introduced as a way to exploit more structure in the latents than simple fully factorized priors, improving compression performance while maintaining end-to-end optimization. Inspired by the success of autoregressive priors in probabilistic generative models, we examine autoregressive, hierarchical, as well as combined priors as alternatives, weighing their costs and benefits in the context of image compression. While it is well known that autoregressive models come with a significant computational penalty, we find that in terms of compression performance, autoregressive and hierarchical priors are complementary and, together, exploit the probabilistic structure in the latents better than all previous learned models. The combined model yields state-of-the-art rate--distortion performance, providing a 15.8% average reduction in file size over the previous state-of-the-art method based on deep learning, which corresponds to a 59.8% size reduction over JPEG, more than 35% reduction compared to WebP and JPEG2000, and bitstreams 8.4% smaller than BPG, the current state-of-the-art image codec. To the best of our knowledge, our model is the first learning-based method to outperform BPG on both PSNR and MS-SSIM distortion metrics.

Key facts. Cited by 642 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 75; 2022: 103; 2023: 110; 2024: 146; 2025: 119; 2026: 88.

642 papers.

Sort:

By area:

  1. 2023Finite Scalar Quantization: VQ-VAE Made Simplecited by 425
  2. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  3. 2021COIN: COmpression with Implicit Neural representationscited by 232
  4. 2021Deep Contextual Video Compressioncited by 216
  5. 2023Learned Image Compression with Mixed Transformer-CNN Architecturescited by 205
  6. 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 193
  7. 2022Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communicationscited by 166
  8. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  9. 2021Implicit Neural Representations for Image Compressioncited by 161
  10. 2023Neural Video Compression with Diverse Contextscited by 155
  11. 2021FVC: A New Framework towards Deep Video Compression in Feature Spacecited by 149
  12. 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 141
38 more
  1. 2022Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compressioncited by 123
  2. 2021Temporal Context Mining for Learned Video Compressioncited by 112
  3. 2021Enhanced Invertible Encoding for Learned Image Compressioncited by 102
  4. 2022Entroformer: A Transformer-based Entropy Model for Learned Image Compressioncited by 102
  5. 2023Towards image compression with perfect realism at ultra-low bitratescited by 99
  6. 2024GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splattingcited by 97
  7. 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Modelscited by 90
  8. 2022COIN++: Neural Compression Across Modalitiescited by 81
  9. 2022MLIC: Multi-Reference Entropy Model for Learned Image Compressioncited by 80
  10. 2024CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splattingcited by 80
  11. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  12. 2022An Introduction to Neural Data Compressioncited by 78
  13. 2022VCT: A Video Compression Transformercited by 74
  14. 2025Improving the Diffusability of Autoencoderscited by 74
  15. 2021Nonlinear Transform Source-Channel Coding for Semantic Communicationscited by 73
  16. 2025Towards Practical Real-Time Neural Video Compressioncited by 72
  17. 2021Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compressioncited by 69
  18. 2021VoxelContext-Net: An Octree based Framework for Point Cloud Compressioncited by 60
  19. 2021Transformer-based Image Compressioncited by 60
  20. 2021Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transformcited by 56
  21. 2023MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compressioncited by 56
  22. 2023Frequency-Aware Transformer for Learned Image Compressioncited by 56
  23. 2024Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Priorcited by 56
  24. 2022Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Predictioncited by 55
  25. 2023C3: High-performance and low-complexity neural compression from a single image or videocited by 54
  26. 2021Joint Global and Local Hierarchical Priors for Learned Image Compressioncited by 52
  27. 2021Lossy Compression for Lossless Predictioncited by 51
  28. 2023WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Modelscited by 51
  29. 2022NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modelingcited by 50
  30. 2022Wireless Deep Video Semantic Transmissioncited by 49
  31. 2021Image coding for machines: an end-to-end learned approachcited by 47
  32. 2023EVC: Towards Real-Time Neural Image Compression with Mask Decaycited by 46
  33. 2022CANF-VC: Conditional Augmented Normalizing Flows for Video Compressioncited by 44
  34. 2024ElasticTok: Adaptive Tokenization for Image and Videocited by 44
  35. 2022Unified Multivariate Gaussian Mixture for Efficient Neural Image Compressioncited by 43
  36. 2022Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compressioncited by 42
  37. 2023Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Triggercited by 40
  38. 2021Overfitting for Fun and Profit: Instance-Adaptive Data Compressioncited by 38

50 most cited of 642 All 642 (JSON)