mlsanityData to 7 Oct 2026

An Introduction to Neural Data Compression

arXiv 2202.06533 ↗First posted 14 Feb 2022cs.LG cs.IT eess.IVcited by 78

Not on the map. Why?

Abstract (arXiv)

Neural compression is the application of neural networks and other machine learning methods to data compression. Recent advances in statistical machine learning have opened up new possibilities for data compression, allowing compression algorithms to be learned end-to-end from data using powerful generative models such as normalizing flows, variational autoencoders, diffusion probabilistic models, and generative adversarial networks. The present article aims to introduce this field of research to a broader machine learning audience by reviewing the necessary background in information theory (e.g., entropy coding, rate-distortion theory) and computer vision (e.g., image quality assessment, perceptual metrics), and providing a curated guide through the essential ideas and methods in the literature thus far.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). Builds on 113 of its 223 references that are in the map. First posted on arXiv 14 Feb 2022.

Builds on

113 of 223 references.

References · 113

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2017Neural Discrete Representation Learningcited by 4,650
  8. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  9. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  10. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  11. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  12. 2015Variational Inference with Normalizing Flowscited by 2,161
38 more
  1. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  2. 2016Density estimation using Real NVPcited by 2,029
  3. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  5. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  6. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  7. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  8. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  9. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  10. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  11. 2016Least Squares Generative Adversarial Networkscited by 1,000
  12. 2016Deep Variational Information Bottleneckcited by 915
  13. 2018Variational image compression with a scale hyperpriorcited by 910
  14. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  15. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  16. 2016Pixel Recurrent Neural Networkscited by 814
  17. 2018Image Transformercited by 770
  18. 2016End-to-end Optimized Image Compressioncited by 673
  19. 2021Vector-quantized Image Modeling with Improved VQGANcited by 656
  20. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  21. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  22. 2017The Perception-Distortion Tradeoffcited by 582
  23. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  24. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  25. 2015Importance Weighted Autoencoderscited by 454
  26. 2020High-Fidelity Generative Image Compressioncited by 331
  27. 2018DVC: An End-to-end Deep Video Compression Frameworkcited by 324
  28. 2018Blockwise Parallel Decoding for Deep Autoregressive Modelscited by 318
  29. 2016Ladder Variational Autoencoderscited by 315
  30. 2015A note on the evaluation of generative modelscited by 291
  31. 2017Lossy Image Compression with Compressive Autoencoderscited by 289
  32. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
  33. 2017Advances in Variational Inferencecited by 236
  34. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 221
  35. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  36. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  37. 2021Autoregressive Diffusion Modelscited by 208
  38. 2016Full Resolution Image Compression with Recurrent Neural Networkscited by 170

50 most cited of 113 All 113 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 11; 2023: 23; 2024: 24; 2025: 14; 2026: 6.

78 papers.

Sort:

By area:

  1. 2022Diffusion Probabilistic Modeling for Video Generationcited by 237
  2. 2022Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communicationscited by 166
  3. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  4. 2022Lossy Compression with Gaussian Diffusioncited by 87
  5. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  6. 2022VCT: A Video Compression Transformercited by 74
  7. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 60
  8. 2023MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compressioncited by 56
  9. 2023C3: High-performance and low-complexity neural compression from a single image or videocited by 54
  10. 2024On the Challenges and Opportunities in Generative AIcited by 31
  11. 2025Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoningcited by 31
  12. 2022Diagnosing and Fixing Manifold Overfitting in Deep Generative Modelscited by 28
38 more
  1. 2023Modality-Agnostic Variational Compression of Implicit Neural Representationscited by 22
  2. 2023Computationally-Efficient Neural Image Compression with Shallow Decoderscited by 22
  3. 2023Semantic Compression With Large Language Modelscited by 17
  4. 2024PerCo (SD): Open Perceptual Compressioncited by 16
  5. 2022SC2 Benchmark: Supervised Compression for Split Computingcited by 14
  6. 2023M2T: Masking Transformers Twice for Faster Decodingcited by 14
  7. 2023Frequency Disentangled Features in Neural Image Compressioncited by 14
  8. 2023EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentationcited by 13
  9. 2022Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utilitycited by 12
  10. 2023FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computingcited by 12
  11. 2024What makes an image realistic?cited by 10
  12. 2024Progressive Compression with Universally Quantized Diffusion Modelscited by 10
  13. 2025Lossy Neural Compression for Geospatial Analytics: A Reviewcited by 10
  14. 2023Fully Bayesian Autoencoders with Latent Sparse Gaussian Processescited by 9
  15. 2023Compression with Exact Error Distribution for Federated Learningcited by 9
  16. 2022Attention-Based Generative Neural Image Compression on Solar Dynamics Observatorycited by 8
  17. 2023ECRF: Entropy-Constrained Neural Radiance Fields Compression with Frequency Domain Optimizationcited by 8
  18. 2024Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Codingcited by 8
  19. 2024Generalized Nested Latent Variable Models for Lossy Coding applied to Wind Turbine Scenarioscited by 7
  20. 2024FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compressioncited by 6
  21. 2023Estimating the Rate-Distortion Function by Wasserstein Gradient Descentcited by 5
  22. 2024Evaluating Large Language Models for Generalization and Robustness via Data Compressioncited by 5
  23. 2025How to Square Tensor Networks and Circuits Without Squaring Themcited by 5
  24. 2024Neural NeRF Compressioncited by 4
  25. 2024Training Foundation Models as Data Compression: On Information, Model Weights and Copyright Lawcited by 4
  26. 2022Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methodscited by 3
  27. 2024Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated Synthesiscited by 3
  28. 2024A Taxonomy of Miscompressions: Preparing Image Forensics for Neural Compressioncited by 3
  29. 2024Neural Networks Generalize on Low Complexity Datacited by 3
  30. 2025Remote Inference over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector Quantizationcited by 3
  31. 2025Generative Diffusion Model-based Compression of MIMO CSIcited by 3
  32. 2023Random Edge Coding: One-Shot Bits-Back Coding of Large Labeled Graphscited by 2
  33. 2023Positional Embedding-Aware Activationscited by 2
  34. 2024Fourier Basis Density Modelcited by 2
  35. 2024Convolutional variational autoencoders for secure lossy image compression in remote sensingcited by 2
  36. 2024Ranking LLMs by compressioncited by 2
  37. 2024On Faster Marginalization with Squared Circuits via Orthonormalizationcited by 2
  38. 2025Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoffcited by 2

50 most cited of 78 All 78 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model
  2. 2024Learned Compression for Compressed Learning
  3. 2025Compact Latent Representation for Image Compression (CLRIC)
  4. 2026Mixture-of-Experts-based Entropy Model for Learned Image Compression
  5. 2026Hybrid Compression: Integrating Pruning and Quantization for Optimized Neural Networks
  6. 2024Sample what you cant compress
  7. 2024Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression
  8. 2025Generative Preprocessing for Image Compression with Pre-trained Diffusion Models