mlsanityData to 7 Oct 2026

Lossy Compression with Gaussian Diffusion

arXiv 2206.08889 ↗First posted 17 Jun 2022stat.ML cs.IT cs.LGcited by 87

On the map: Diffusion models → Diffusion for compression and wireless

Abstract (arXiv)

We consider a novel lossy compression approach based on unconditional diffusion generative models, which we call DiffC. Unlike modern compression schemes which rely on transform coding and quantization to restrict the transmitted information, DiffC relies on the efficient communication of pixels corrupted by Gaussian noise. We implement a proof of concept and find that it works surprisingly well despite the lack of an encoder transform, outperforming the state-of-the-art generative compression method HiFiC on ImageNet 64x64. DiffC only uses a single model to encode and denoise corrupted pixels at arbitrary bitrates. The approach further provides support for progressive coding, that is, decoding from partial bit streams. We perform a rate-distortion analysis to gain a deeper understanding of its performance, providing analytical results for multivariate Gaussian data as well as theoretic bounds for general distributions. Furthermore, we prove that a flow-based reconstruction achieves a 3 dB gain over ancestral sampling at high bitrates.

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). Placed in Diffusion for compression and wireless, one of 14 directions in Diffusion models. Builds on 43 of its 69 references that are in the map. First posted on arXiv 17 Jun 2022.

Builds on

43 of 69 references.

References · 43

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  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. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  9. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  10. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  11. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  12. 2016Pixel Recurrent Neural Networkscited by 814
31 more
  1. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 773
  2. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
  3. 2021SoundStream: An End-to-End Neural Audio Codeccited by 756
  4. 2016End-to-end Optimized Image Compressioncited by 673
  5. 2021Score-based Generative Modeling in Latent Spacecited by 634
  6. 2017The Perception-Distortion Tradeoffcited by 582
  7. 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 526
  8. 2020High-Fidelity Generative Image Compressioncited by 331
  9. 2017Lossy Image Compression with Compressive Autoencoderscited by 289
  10. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusioncited by 230
  11. 2021Gotta Go Fast When Generating Data with Score-Based Modelscited by 218
  12. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  13. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 207
  14. 2019Generalized Sliced Wasserstein Distancescited by 205
  15. 2021On Fast Sampling of Diffusion Probabilistic Modelscited by 170
  16. 2020Nonlinear Transform Codingcited by 132
  17. 2021Learning to Efficiently Sample from Diffusion Probabilistic Modelscited by 129
  18. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latentscited by 103
  19. 2020Interacting particle solutions of Fokker-Planck equations through gradient-log-density estimationcited by 87
  20. 2022An Introduction to Neural Data Compressioncited by 78
  21. 2020Universally Quantized Neural Compressioncited by 60
  22. 2018Deep Generative Models for Distribution-Preserving Lossy Compressioncited by 59
  23. 2018Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameterscited by 56
  24. 2021Universal Rate-Distortion-Perception Representations for Lossy Compressioncited by 46
  25. 2020Compressing Images by Encoding Their Latent Representations with Relative Entropy Codingcited by 36
  26. 2021Algorithms for the Communication of Samplescited by 31
  27. 2021A coding theorem for the rate-distortion-perception functioncited by 30
  28. 2021On the advantages of stochastic encoderscited by 28
  29. 2021On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Frameworkcited by 27
  30. 2022The Rate-Distortion-Perception Tradeoff: The Role of Common Randomnesscited by 21
  31. 2019Exact Rate-Distortion in Autoencoders via Echo Noisecited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 11; 2023: 17; 2024: 18; 2025: 20; 2026: 21.

87 papers.

Sort:

By area:

  1. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  2. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  3. 2022A Survey on Generative Diffusion Modelcited by 238
  4. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  5. 2023Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learningcited by 145
  6. 2023Editing Implicit Assumptions in Text-to-Image Diffusion Modelscited by 128
  7. 2024Neural Video Compression with Feature Modulationcited by 115
  8. 2023Towards image compression with perfect realism at ultra-low bitratescited by 99
  9. 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Modelscited by 90
  10. 2022Blurring Diffusion Modelscited by 89
  11. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  12. 2023Text + Sketch: Image Compression at Ultra Low Ratescited by 63
38 more
  1. 2024Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Priorcited by 56
  2. 2023High-Fidelity Image Compression with Score-based Generative Modelscited by 53
  3. 2023GSURE-Based Diffusion Model Training with Corrupted Datacited by 40
  4. 2022Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidancecited by 33
  5. 2023A Residual Diffusion Model for High Perceptual Quality Codec Augmentationcited by 33
  6. 2022Extreme Generative Image Compression by Learning Text Embedding from Diffusion Modelscited by 30
  7. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 29
  8. 2024Idempotence and Perceptual Image Compressioncited by 27
  9. 2023Compression with Bayesian Implicit Neural Representationscited by 25
  10. 2025Compressed Image Generation with Denoising Diffusion Codebook Modelscited by 24
  11. 2025Lossy Compression with Pretrained Diffusion Modelscited by 23
  12. 2023Modality-Agnostic Variational Compression of Implicit Neural Representationscited by 22
  13. 2023Just One Byte (per gradient): A Note on Low-Bandwidth Decentralized Language Model Finetuning Using Shared Randomnesscited by 18
  14. 2025Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusioncited by 17
  15. 2024Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Modelcited by 16
  16. 2022Do Perceptually Aligned Gradients Imply Adversarial Robustness?cited by 15
  17. 2023EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentationcited by 13
  18. 2024Diffusion-Aided Joint Source Channel Coding For High Realism Wireless Image Transmissioncited by 11
  19. 2024Progressive Compression with Universally Quantized Diffusion Modelscited by 10
  20. 2023Compression with Exact Error Distribution for Federated Learningcited by 9
  21. 2024Applications of Generative AI (GAI) for Mobile and Wireless Networking: A Surveycited by 9
  22. 2025GIViC: Generative Implicit Video Compressioncited by 9
  23. 2025CoD: A Diffusion Foundation Model for Image Compressioncited by 9
  24. 2023ECSIC: Epipolar Cross Attention for Stereo Image Compressioncited by 8
  25. 2023Wasserstein Distortion: Unifying Fidelity and Realismcited by 8
  26. 2024Universal Exact Compression of Differentially Private Mechanismscited by 8
  27. 2025Generative Latent Video Compressioncited by 8
  28. 2024The Rate-Distortion-Perception Trade-off: The Role of Private Randomnesscited by 6
  29. 2023High-dimensional Asymptotics of VAEs: Threshold of Posterior Collapse and Dataset-Size Dependence of Rate-Distortion Curvecited by 5
  30. 2023On the Computation of the Gaussian Rate-Distortion-Perception Functioncited by 5
  31. 2024PSC: Posterior Sampling-Based Compressioncited by 5
  32. 2024Some Notes on the Sample Complexity of Approximate Channel Simulationcited by 4
  33. 2024Accelerating Relative Entropy Coding with Space Partitioningcited by 4
  34. 2025Synonymous Variational Inference for Perceptual Image Compressioncited by 4
  35. 2025Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compressioncited by 4
  36. 2025Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Priorcited by 4
  37. 2025Ultra-Low Bitrate Perceptual Image Compression with Shallow Encodercited by 4
  38. 2026Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Texturescited by 4

50 most cited of 87 All 87 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Lossy Image Compression with Foundation Diffusion Models
  2. 2025Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression
  3. 2025OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates
  4. 2026Towards Efficient Low-rate Image Compression with Frequency-aware Diffusion Prior Refinement
  5. 2025HDCompression: Hybrid-Diffusion Image Compression for Ultra-Low Bitrates
  6. 2025Generative Image Compression by Estimating Gradients of the Rate-variable Feature Distribution
  7. 2024DiffCom: Channel Received Signal is a Natural Condition to Guide Diffusion Posterior Sampling
  8. 2025Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression