mlsanityData to 7 Oct 2026

A Residual Diffusion Model for High Perceptual Quality Codec Augmentation

arXiv 2301.05489 ↗First posted 13 Jan 2023cs.CV eess.IVcited by 33

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

Abstract (arXiv)

Diffusion probabilistic models have recently achieved remarkable success in generating high quality image and video data. In this work, we build on this class of generative models and introduce a method for lossy compression of high resolution images. The resulting codec, which we call DIffuson-based Residual Augmentation Codec (DIRAC), is the first neural codec to allow smooth traversal of the rate-distortion-perception tradeoff at test time, while obtaining competitive performance with GAN-based methods in perceptual quality. Furthermore, while sampling from diffusion probabilistic models is notoriously expensive, we show that in the compression setting the number of steps can be drastically reduced.

Key facts. Cited by 33 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 63 of its 78 references that are in the map. First posted on arXiv 13 Jan 2023.

Builds on

63 of 78 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022Extreme Generative Image Compression by Learning Text Embedding from Diffusion Models14 Nov
  2. 2022Lossy Image Compression with Conditional Diffusion Models14 Sep
  3. 2022Lossy Compression with Gaussian Diffusion17 Jun

Other references · 60

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2020Denoising Diffusion Implicit Modelscited by 9,655
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  8. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  9. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  10. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  11. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  12. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
38 more
  1. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  2. 2022Video Diffusion Modelscited by 2,280
  3. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  4. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  5. 2018Demystifying MMD GANscited by 1,268
  6. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  7. 2021Variational Diffusion Modelscited by 1,145
  8. 2022Denoising Diffusion Restoration Modelscited by 951
  9. 2018Variational image compression with a scale hyperpriorcited by 910
  10. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  11. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 447
  12. 2020High-Fidelity Generative Image Compressioncited by 331
  13. 2018DVC: An End-to-end Deep Video Compression Frameworkcited by 324
  14. 2017Lossy Image Compression with Compressive Autoencoderscited by 289
  15. 2020CompressAI: a PyTorch library and evaluation platform for end-to-end compression researchcited by 271
  16. 2016Learning Representations for Automatic Colorizationcited by 251
  17. 2021Deblurring via Stochastic Refinementcited by 248
  18. 2022Diffusion Probabilistic Modeling for Video Generationcited by 237
  19. 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
  20. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  21. 2021Autoregressive Diffusion Modelscited by 208
  22. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 207
  23. 2021FVC: A New Framework towards Deep Video Compression in Feature Spacecited by 149
  24. 2018Video Compression through Image Interpolationcited by 143
  25. 2015Compression Artifacts Reduction by a Deep Convolutional Networkcited by 136
  26. 2017Real-Time Adaptive Image Compressioncited by 127
  27. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latentscited by 103
  28. 2022Accelerating Diffusion Models via Early Stop of the Diffusion Processcited by 100
  29. 2019Video Compression With Rate-Distortion Autoencoderscited by 97
  30. 2018Learned Video Compressioncited by 89
  31. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  32. 2021ELF-VC: Efficient Learned Flexible-Rate Video Codingcited by 68
  33. 2018Deep Generative Models for Distribution-Preserving Lossy Compressioncited by 59
  34. 2020Quantization Guided JPEG Artifact Correctioncited by 57
  35. 2021Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transformcited by 56
  36. 2022Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Predictioncited by 55
  37. 2021Soft then Hard: Rethinking the Quantization in Neural Image Compressioncited by 50
  38. 2022JPEG Artifact Correction using Denoising Diffusion Restoration Modelscited by 45

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 12; 2025: 9; 2026: 9.

33 papers.

Sort:

By area:

  1. 2023Towards image compression with perfect realism at ultra-low bitratescited by 99
  2. 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Modelscited by 90
  3. 2024Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Priorcited by 56
  4. 2025Compressed Image Generation with Denoising Diffusion Codebook Modelscited by 24
  5. 2025Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusioncited by 17
  6. 2024Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Modelcited by 16
  7. 2024All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregationcited by 14
  8. 2023EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentationcited by 13
  9. 2024Extreme Video Compression with Pre-trained Diffusion Modelscited by 6
  10. 2024Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compressioncited by 6
  11. 2024PSC: Posterior Sampling-Based Compressioncited by 5
  12. 2024High Frequency Matters: Uncertainty Guided Image Compression with Wavelet Diffusioncited by 4
21 more
  1. 2025Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compressioncited by 4
  2. 2025Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Priorcited by 4
  3. 2026Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Texturescited by 4
  4. 2026Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compressioncited by 4
  5. 2024Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated Synthesiscited by 3
  6. 2025Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compressioncited by 3
  7. 2024Low-Latency Neural Stereo Streamingcited by 2
  8. 2024Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimizationcited by 2
  9. 2024Neural Graphics Texture Compression Supporting Random Accesscited by 2
  10. 2025Why Compress What You Can Generate? When GPT-4o Generation Ushers in Image Compression Fieldscited by 2
  11. 2026Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priorscited by 2
  12. 2025Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion modelcited by 1
  13. 2025Generative Image Coding with Diffusion Priorcited by 1
  14. 2026Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compressioncited by 1
  15. 2024Towards Defining an Efficient and Expandable File Format for AI-Generated Contentscited by 0
  16. 2025Comp-X: On Defining an Interactive Learned Image Compression Paradigm With Expert-driven LLM Agentcited by 0
  17. 2026A PPO-Based Bitrate Allocation Conditional Diffusion Model for Remote Sensing Image Compressioncited by 0
  18. 2026Joint Degradation-Aware Arbitrary-Scale Super-Resolution for Variable-Rate Extreme Image Compressioncited by 0
  19. 2026Region-Adaptive Generative Compression with Spatially Varying Diffusion Modelscited by 0
  20. 2026A Noise Constrained Diffusion (NC-Diffusion) Framework for High Fidelity Image Compressioncited by 0
  21. 2026Rethinking Generative Image Compression at Extremely Low Bitratescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Single-step Diffusion for Image Compression at Ultra-Low Bitrates
  2. 2026One-Step Diffusion for Perceptual Image Compression
  3. 2024Enhancing the Rate-Distortion-Perception Flexibility of Learned Image Codecs with Conditional Diffusion Decoders
  4. 2023High-Fidelity Image Compression with Score-based Generative Models
  5. 2025Generative Preprocessing for Image Compression with Pre-trained Diffusion Models
  6. 2025HDCompression: Hybrid-Diffusion Image Compression for Ultra-Low Bitrates
  7. 2026DiffCVE: Diffusion-based Compressed Video Enhancement
  8. 2024Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder