mlsanityData to 7 Oct 2026

Towards image compression with perfect realism at ultra-low bitrates

arXiv 2310.10325 ↗First posted 16 Oct 2023cs.CV eess.IVcited by 99

Not on the map. Why?

Cited by 48 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image codecs are typically optimized to trade-off bitrate vs distortion metrics. At low bitrates, this leads to compression artefacts which are easily perceptible, even when training with perceptual or adversarial losses. To improve image quality and remove dependency on the bitrate, we propose to decode with iterative diffusion models. We condition the decoding process on a vector-quantized image representation, as well as a global image description to provide additional context. We dub our model PerCo for 'perceptual compression', and compare it to state-of-the-art codecs at rates from 0.1 down to 0.003 bits per pixel. The latter rate is more than an order of magnitude smaller than those considered in most prior work, compressing a 512x768 Kodak image with less than 153 bytes. Despite this ultra-low bitrate, our approach maintains the ability to reconstruct realistic images. We find that our model leads to reconstructions with state-of-the-art visual quality as measured by FID and KID. As predicted by rate-distortion-perception theory, visual quality is less dependent on the bitrate than previous methods.

Key facts. Cited by 99 papers in the map (data through 7 Oct 2026). Builds on 42 of its 55 references that are in the map. First posted on arXiv 16 Oct 2023.

Builds on

42 of 55 references.

References · 42

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  8. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2017Neural Discrete Representation Learningcited by 4,650
  11. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  12. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
30 more
  1. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  2. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  3. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  4. 2018Demystifying MMD GANscited by 1,268
  5. 2021Variational Diffusion Modelscited by 1,145
  6. 2018Variational image compression with a scale hyperpriorcited by 910
  7. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  8. 2016End-to-end Optimized Image Compressioncited by 673
  9. 2021Vector-quantized Image Modeling with Improved VQGANcited by 656
  10. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  11. 2017The Perception-Distortion Tradeoffcited by 582
  12. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  13. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  14. 2020High-Fidelity Generative Image Compressioncited by 331
  15. 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discoverycited by 329
  16. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  17. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
  18. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  19. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 207
  20. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  21. 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Modelscited by 90
  22. 2022Lossy Compression with Gaussian Diffusioncited by 87
  23. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  24. 2023Text + Sketch: Image Compression at Ultra Low Ratescited by 63
  25. 2023High-Fidelity Image Compression with Score-based Generative Modelscited by 53
  26. 2022PO-ELIC: Perception-Oriented Efficient Learned Image Codingcited by 35
  27. 2023A Residual Diffusion Model for High Perceptual Quality Codec Augmentationcited by 33
  28. 2022Image Compression with Product Quantized Masked Image Modelingcited by 32
  29. 2022Extreme Generative Image Compression by Learning Text Embedding from Diffusion Modelscited by 30
  30. 2023Conditional Perceptual Quality Preserving Image Compressioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 19; 2025: 46; 2026: 34.

99 papers.

Sort:

By area:

  1. 2024Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Priorcited by 56
  2. 2024Consistency-diversity-realism Pareto fronts of conditional image generative modelscited by 35
  3. 2024Lossy Image Compression with Foundation Diffusion Modelscited by 34
  4. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 29
  5. 2025Compressed Image Generation with Denoising Diffusion Codebook Modelscited by 24
  6. 2025Lossy Compression with Pretrained Diffusion Modelscited by 23
  7. 2025One-Step Diffusion-Based Image Compression with Semantic Distillationcited by 23
  8. 2025Generative Latent Coding for Ultra-Low Bitrate Image and Video Compressioncited by 22
  9. 2024RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusioncited by 21
  10. 2025Generative Latent Coding for Ultra-Low Bitrate Image Compressioncited by 21
  11. 2024Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelitycited by 20
  12. 2025DLF: Extreme Image Compression with Dual-generative Latent Fusioncited by 20
38 more
  1. 2025Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusioncited by 17
  2. 2024PerCo (SD): Open Perceptual Compressioncited by 16
  3. 2025Semantics-Guided Diffusion for Deep Joint Source-Channel Coding in Wireless Image Transmissioncited by 15
  4. 2024On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Modelscited by 12
  5. 2024Diffusion-Aided Joint Source Channel Coding For High Realism Wireless Image Transmissioncited by 11
  6. 2024What makes an image realistic?cited by 10
  7. 2024Progressive Compression with Universally Quantized Diffusion Modelscited by 10
  8. 2025PICD: Versatile Perceptual Image Compression with Diffusion Renderingcited by 10
  9. 2024M3-CVC: Controllable Video Compression with Multimodal Generative Modelscited by 9
  10. 2025Generative Video Semantic Communication via Multimodal Semantic Fusion with Large Modelcited by 9
  11. 2025CoD: A Diffusion Foundation Model for Image Compressioncited by 9
  12. 2024Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compressioncited by 8
  13. 2025Generative Latent Video Compressioncited by 8
  14. 2025Single-step Diffusion-based Video Coding with Semantic-Temporal Guidancecited by 8
  15. 2025Qinco2: Vector Compression and Search with Improved Implicit Neural Codebookscited by 7
  16. 2025Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compressioncited by 7
  17. 2025SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenizationcited by 7
  18. 2024PSC: Posterior Sampling-Based Compressioncited by 5
  19. 2024Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMscited by 5
  20. 2025Conditional Video Generation for High-Efficiency Video Compressioncited by 5
  21. 2024LMM-driven Semantic Image-Text Coding for Ultra Low-bitrate Learned Image Compressioncited by 4
  22. 2025Extremely low-bitrate Image Compression Semantically Disentangled by LMMs from a Human Perception Perspectivecited by 4
  23. 2025Synonymous Variational Inference for Perceptual Image Compressioncited by 4
  24. 2025Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compressioncited by 4
  25. 2025Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Priorcited by 4
  26. 2025Ultra-Low Bitrate Perceptual Image Compression with Shallow Encodercited by 4
  27. 2026Diffusion-aided Extreme Video Compression with Lightweight Semantics Guidancecited by 4
  28. 2026Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Texturescited by 4
  29. 2026Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compressioncited by 4
  30. 2026CoD-Lite: Real-Time Diffusion-Based Generative Image Compressioncited by 4
  31. 2024Map-Assisted Remote-Sensing Image Compression at Extremely Low Bitratescited by 3
  32. 2025Guaranteed Conditional Diffusion: 3D Block-based Models for Scientific Data Compressioncited by 3
  33. 2025Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compressioncited by 3
  34. 2026DiT-IC: Aligned Diffusion Transformer for Efficient Image Compressioncited by 3
  35. 2024Unicorn: Unified Neural Image Compression with One Number Reconstructioncited by 2
  36. 2025Why Compress What You Can Generate? When GPT-4o Generation Ushers in Image Compression Fieldscited by 2
  37. 2025Single-step Diffusion for Image Compression at Ultra-Low Bitratescited by 2
  38. 2025SLIM: Semantic-based Low-bitrate Image compression for Machines by leveraging diffusioncited by 2

50 most cited of 99 All 99 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Enhancing the Rate-Distortion-Perception Flexibility of Learned Image Codecs with Conditional Diffusion Decoders
  2. 2025HDCompression: Hybrid-Diffusion Image Compression for Ultra-Low Bitrates
  3. 2026One-Step Diffusion for Perceptual Image Compression
  4. 2024UniMIC: Towards Universal Multi-modality Perceptual Image Compression
  5. 2025Versatile Recompression-Aware Perceptual Image Super-Resolution
  6. 2025Generative Preprocessing for Image Compression with Pre-trained Diffusion Models
  7. 2026Training-Free Rate-Distortion-Perception Traversal With Diffusion
  8. 2026PULSE: Unlocking Practical Image Compression on Single-Thread CPU