mlsanityData to 7 Oct 2026

High-Fidelity Image Compression with Score-based Generative Models

arXiv 2305.18231 ↗First posted 26 May 2023eess.IV cs.CV cs.LGcited by 53

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

Abstract (arXiv)

Despite the tremendous success of diffusion generative models in text-to-image generation, replicating this success in the domain of image compression has proven difficult. In this paper, we demonstrate that diffusion can significantly improve perceptual quality at a given bit-rate, outperforming state-of-the-art approaches PO-ELIC and HiFiC as measured by FID score. This is achieved using a simple but theoretically motivated two-stage approach combining an autoencoder targeting MSE followed by a further score-based decoder. However, as we will show, implementation details matter and the optimal design decisions can differ greatly from typical text-to-image models.

Key facts. Cited by 53 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 38 of its 47 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

38 of 47 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Lossy Image Compression with Conditional Diffusion Models14 Sep
  2. 2022Lossy Compression with Gaussian Diffusion17 Jun

Other references · 36

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  10. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  11. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  12. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
24 more
  1. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  2. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  3. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  4. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  5. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  6. 2017The Perception-Distortion Tradeoffcited by 582
  7. 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 413
  8. 2020High-Fidelity Generative Image Compressioncited by 331
  9. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  10. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
  11. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  12. 2023On the Importance of Noise Scheduling for Diffusion Modelscited by 193
  13. 2022Scalable Adaptive Computation for Iterative Generationcited by 190
  14. 2017Real-Time Adaptive Image Compressioncited by 127
  15. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  16. 2018Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameterscited by 56
  17. 2021Universal Rate-Distortion-Perception Representations for Lossy Compressioncited by 46
  18. 2017Generative Compressioncited by 40
  19. 2022PO-ELIC: Perception-Oriented Efficient Learned Image Codingcited by 35
  20. 2022Towards Semantic Communications: Deep Learning-Based Image Semantic Codingcited by 35
  21. 2022Image Compression with Product Quantized Masked Image Modelingcited by 32
  22. 2021Algorithms for the Communication of Samplescited by 31
  23. 2021On the advantages of stochastic encoderscited by 28
  24. 2020A GAN-based Tunable Image Compression Systemcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 19; 2025: 20; 2026: 11.

53 papers.

Sort:

By area:

  1. 2023Towards image compression with perfect realism at ultra-low bitratescited by 99
  2. 2025Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenizationcited by 35
  3. 2024Lossy Image Compression with Foundation Diffusion Modelscited by 34
  4. 2024MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Modelcited by 29
  5. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 29
  6. 2024Idempotence and Perceptual Image Compressioncited by 27
  7. 2025Generative Latent Coding for Ultra-Low Bitrate Image and Video Compressioncited by 22
  8. 2025Generative Latent Coding for Ultra-Low Bitrate Image Compressioncited by 21
  9. 2024Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelitycited by 20
  10. 2025Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusioncited by 17
  11. 2023DORSal: Diffusion for Object-centric Representations of Scenes et alcited by 16
  12. 2024Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Modelcited by 16
38 more
  1. 2024Epsilon-VAE: Denoising as Visual Decodingcited by 16
  2. 2023EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentationcited by 13
  3. 2024Progressive Compression with Universally Quantized Diffusion Modelscited by 10
  4. 2025PICD: Versatile Perceptual Image Compression with Diffusion Renderingcited by 10
  5. 2025Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compressioncited by 7
  6. 2025SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenizationcited by 7
  7. 2024Extreme Video Compression with Pre-trained Diffusion Modelscited by 6
  8. 2024Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compressioncited by 6
  9. 2024PSC: Posterior Sampling-Based Compressioncited by 5
  10. 2024High Frequency Matters: Uncertainty Guided Image Compression with Wavelet Diffusioncited by 4
  11. 2024Sample what you cant compresscited by 4
  12. 2024LMM-driven Semantic Image-Text Coding for Ultra Low-bitrate Learned Image Compressioncited by 4
  13. 2024Is JPEG AI going to change image forensics?cited by 4
  14. 2025Synonymous Variational Inference for Perceptual Image Compressioncited by 4
  15. 2025Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Priorcited by 4
  16. 2025Ultra-Low Bitrate Perceptual Image Compression with Shallow Encodercited by 4
  17. 2026Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compressioncited by 4
  18. 2024COSMIC: Compress Satellite Images Efficiently via Diffusion Compensationcited by 3
  19. 2024Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimizationcited by 2
  20. 2025Why Compress What You Can Generate? When GPT-4o Generation Ushers in Image Compression Fieldscited by 2
  21. 2025Single-step Diffusion for Image Compression at Ultra-Low Bitratescited by 2
  22. 2026Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priorscited by 2
  23. 2026GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flowcited by 2
  24. 2024Extreme Compression of Adaptive Neural Imagescited by 1
  25. 2025Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion modelcited by 1
  26. 2025Generative Image Compression by Estimating Gradients of the Rate-variable Feature Distributioncited by 1
  27. 2025Generative Image Coding with Diffusion Priorcited by 1
  28. 2025VLIC: Vision-Language Models As Perceptual Judges for Human-Aligned Image Compressioncited by 1
  29. 2026Efficient Video Diffusion with Sparse Information Transmission for Video Compressioncited by 1
  30. 2024Trustworthy Compression? Impact of AI-based Codecs on Biometrics for Law Enforcementcited by 0
  31. 2024Towards Defining an Efficient and Expandable File Format for AI-Generated Contentscited by 0
  32. 2025Three Forensic Cues for JPEG AI Imagescited by 0
  33. 2025Fast Training-free Perceptual Image Compressioncited by 0
  34. 2025Keep It Real: Challenges in Attacking Compression-Based Adversarial Purificationcited by 0
  35. 2026Advances in Diffusion-Based Generative Compressioncited by 0
  36. 2026Region-Adaptive Generative Compression with Spatially Varying Diffusion Modelscited by 0
  37. 2026On the Robustness of Diffusion-Based Image Compression to Bit-Flip Errorscited by 0
  38. 2026A Noise Constrained Diffusion (NC-Diffusion) Framework for High Fidelity Image Compressioncited by 0

50 most cited of 53 All 53 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022Extreme Generative Image Compression by Learning Text Embedding from Diffusion Models
  2. 2026CoD-Lite: Real-Time Diffusion-Based Generative Image Compression
  3. 2025One-Step Diffusion-Based Image Compression with Semantic Distillation
  4. 2024Enhancing the Rate-Distortion-Perception Flexibility of Learned Image Codecs with Conditional Diffusion Decoders
  5. 2025Generative Preprocessing for Image Compression with Pre-trained Diffusion Models
  6. 2025Compressed Image Generation with Denoising Diffusion Codebook Models
  7. 2026One-Step Diffusion for Perceptual Image Compression
  8. 2024Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder