mlsanityData to 7 Oct 2026

Idempotence and Perceptual Image Compression

arXiv 2401.08920 ↗First posted 17 Jan 2024eess.IV cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Idempotence is the stability of image codec to re-compression. At the first glance, it is unrelated to perceptual image compression. However, we find that theoretically: 1) Conditional generative model-based perceptual codec satisfies idempotence; 2) Unconditional generative model with idempotence constraint is equivalent to conditional generative codec. Based on this newfound equivalence, we propose a new paradigm of perceptual image codec by inverting unconditional generative model with idempotence constraints. Our codec is theoretically equivalent to conditional generative codec, and it does not require training new models. Instead, it only requires a pre-trained mean-square-error codec and unconditional generative model. Empirically, we show that our proposed approach outperforms state-of-the-art methods such as HiFiC and ILLM, in terms of Fr'echet Inception Distance (FID). The source code is provided in https://github.com/tongdaxu/Idempotence-and-Perceptual-Image-Compression.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 48 of its 64 references that are in the map. First posted on arXiv 17 Jan 2024.

Builds on

48 of 64 references.

References · 48

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2022Classifier-Free Diffusion Guidancecited by 5,717
  7. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  8. 2018Variational image compression with a scale hyperpriorcited by 910
  9. 2016End-to-end Optimized Image Compressioncited by 673
  10. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  11. 2017Video Enhancement with Task-Oriented Flowcited by 612
  12. 2017The Perception-Distortion Tradeoffcited by 582
36 more
  1. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
  2. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  3. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 501
  4. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  5. 2018Assessing Generative Models via Precision and Recallcited by 401
  6. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  7. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  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. 2020CompressAI: a PyTorch library and evaluation platform for end-to-end compression researchcited by 271
  11. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
  12. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 207
  13. 2023Learned Image Compression with Mixed Transformer-CNN Architecturescited by 205
  14. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  15. 2020You Only Need Adversarial Supervision for Semantic Image Synthesiscited by 129
  16. 2017Real-Time Adaptive Image Compressioncited by 127
  17. 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Modelscited by 90
  18. 2022Lossy Compression with Gaussian Diffusioncited by 87
  19. 2019Practical Lossless Compression with Latent Variables using Bits Back Codingcited by 85
  20. 2021HyperInverter: Improving StyleGAN Inversion via Hypernetworkcited by 85
  21. 2020Improving Inference for Neural Image Compressioncited by 81
  22. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  23. 2021Intermediate Layer Optimization for Inverse Problems using Deep Generative Modelscited by 70
  24. 2018Deep Generative Models for Distribution-Preserving Lossy Compressioncited by 59
  25. 2023High-Fidelity Image Compression with Score-based Generative Modelscited by 53
  26. 2021A Theory of the Distortion-Perception Tradeoff in Wasserstein Spacecited by 52
  27. 2022PO-ELIC: Perception-Oriented Efficient Learned Image Codingcited by 35
  28. 2020Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networkscited by 28
  29. 2021On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Frameworkcited by 27
  30. 2020Lossy Image Compression with Normalizing Flowscited by 25
  31. 2022Optimally Controllable Perceptual Lossy Compressioncited by 13
  32. 2022Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Qualitycited by 13
  33. 2022Dimensionality-Varying Diffusion Processcited by 12
  34. 2022Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problemscited by 11
  35. 2022High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformationcited by 8
  36. 2022Multi-Sample Training for Neural Image Compressioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 16; 2026: 5.

27 papers.

Sort:

By area:

  1. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 29
  2. 2025Compressed Image Generation with Denoising Diffusion Codebook Modelscited by 24
  3. 2025OSCAR: One-Step Diffusion Codec Across Multiple Bit-ratescited by 24
  4. 2025Lossy Compression with Pretrained Diffusion Modelscited by 23
  5. 2024Lossless data compression by large modelscited by 20
  6. 2025DLF: Extreme Image Compression with Dual-generative Latent Fusioncited by 20
  7. 2024Bidirectional Consistency Modelscited by 18
  8. 2025Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusioncited by 17
  9. 2025PICD: Versatile Perceptual Image Compression with Diffusion Renderingcited by 10
  10. 2025CoD: A Diffusion Foundation Model for Image Compressioncited by 9
  11. 2024Idempotent Unsupervised Representation Learning for Skeleton-Based Action Recognitioncited by 7
  12. 2024PSC: Posterior Sampling-Based Compressioncited by 5
15 more
  1. 2025Synonymous Variational Inference for Perceptual Image Compressioncited by 4
  2. 2025Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compressioncited by 4
  3. 2025Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Priorcited by 4
  4. 2025Ultra-Low Bitrate Perceptual Image Compression with Shallow Encodercited by 4
  5. 2026CoD-Lite: Real-Time Diffusion-Based Generative Image Compressioncited by 4
  6. 2024Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimizationcited by 2
  7. 2026Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priorscited by 2
  8. 2025SS-DC: Spatial-Spectral Decoupling and Coupling Across Visible-Infrared Gap for Domain Adaptive Object Detectioncited by 1
  9. 2025Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communicationscited by 1
  10. 2026TextBoost: Boosting Scene Text Fidelity in Ultra-low Bitrate Image Compressioncited by 1
  11. 2024Towards Defining an Efficient and Expandable File Format for AI-Generated Contentscited by 0
  12. 2025Fast Training-free Perceptual Image Compressioncited by 0
  13. 2025Keep It Real: Challenges in Attacking Compression-Based Adversarial Purificationcited by 0
  14. 2026Dual-Constrained Diffusion Image Compression for Operational Rate-Distortion-Perception Optimizationcited by 0
  15. 2026Group-of-Latents: Perceptual Video Compression at Extreme Bitrates via Masked Latent Generative Modelingcited by 0