mlsanityData to 7 Oct 2026

Multi-Realism Image Compression with a Conditional Generator

arXiv 2212.13824 ↗First posted 28 Dec 2022cs.CV cs.LG eess.IVcited by 79

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

By optimizing the rate-distortion-realism trade-off, generative compression approaches produce detailed, realistic images, even at low bit rates, instead of the blurry reconstructions produced by rate-distortion optimized models. However, previous methods do not explicitly control how much detail is synthesized, which results in a common criticism of these methods: users might be worried that a misleading reconstruction far from the input image is generated. In this work, we alleviate these concerns by training a decoder that can bridge the two regimes and navigate the distortion-realism trade-off. From a single compressed representation, the receiver can decide to either reconstruct a low mean squared error reconstruction that is close to the input, a realistic reconstruction with high perceptual quality, or anything in between. With our method, we set a new state-of-the-art in distortion-realism, pushing the frontier of achievable distortion-realism pairs, i.e., our method achieves better distortions at high realism and better realism at low distortion than ever before.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). Builds on 35 of its 48 references that are in the map. First posted on arXiv 28 Dec 2022.

Builds on

35 of 48 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  6. 2014Conditional Generative Adversarial Netscited by 2,152
  7. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  8. 2018Variational image compression with a scale hyperpriorcited by 910
  9. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  10. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  11. 2020High-Fidelity Generative Image Compressioncited by 331
  12. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
23 more
  1. 2017Lossy Image Compression with Compressive Autoencoderscited by 289
  2. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
  3. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  4. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 207
  5. 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 193
  6. 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 141
  7. 2020Nonlinear Transform Codingcited by 132
  8. 2018Conditional Probability Models for Deep Image Compressioncited by 128
  9. 2017Real-Time Adaptive Image Compressioncited by 127
  10. 2022Lossy Compression with Gaussian Diffusioncited by 87
  11. 2022An Introduction to Neural Data Compressioncited by 78
  12. 2018Deep Generative Models for Distribution-Preserving Lossy Compressioncited by 59
  13. 2021Universal Rate-Distortion-Perception Representations for Lossy Compressioncited by 46
  14. 2022Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compressioncited by 42
  15. 2017Generative Compressioncited by 40
  16. 2021Perceptual Learned Video Compression with Recurrent Conditional GANcited by 38
  17. 2022PO-ELIC: Perception-Oriented Efficient Learned Image Codingcited by 35
  18. 2021Algorithms for the Communication of Samplescited by 31
  19. 2021A coding theorem for the rate-distortion-perception functioncited by 30
  20. 2020Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networkscited by 28
  21. 2021On the advantages of stochastic encoderscited by 28
  22. 2022Flexible Neural Image Compression via Code Editingcited by 19
  23. 2022Content-oriented learned image compressioncited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 14; 2024: 27; 2025: 24; 2026: 14.

79 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. 2023High-Fidelity Image Compression with Score-based Generative Modelscited by 53
  4. 2024Lossy Image Compression with Foundation Diffusion Modelscited by 34
  5. 2023A Residual Diffusion Model for High Perceptual Quality Codec Augmentationcited by 33
  6. 2024Joint Source-Channel Coding: Fundamentals and Recent Progress in Practical Designscited by 32
  7. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 29
  8. 2024Idempotence and Perceptual Image Compressioncited by 27
  9. 2025One-Step Diffusion-Based Image Compression with Semantic Distillationcited by 23
  10. 2025Generative Latent Coding for Ultra-Low Bitrate Image and Video Compressioncited by 22
  11. 2025Generative Latent Coding for Ultra-Low Bitrate Image Compressioncited by 21
  12. 2024Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelitycited by 20
38 more
  1. 2024Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Modelcited by 16
  2. 2024Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptationcited by 15
  3. 2023M2T: Masking Transformers Twice for Faster Decodingcited by 14
  4. 2024All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregationcited by 14
  5. 2023EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentationcited by 13
  6. 2023A Review of Change of Variable Formulas for Generative Modelingcited by 12
  7. 2024Unifying Generation and Compression: Ultra-low bitrate Image Coding Via Multi-stage Transformercited by 11
  8. 2024Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decodercited by 11
  9. 2024Rate-Distortion-Cognition Controllable Versatile Neural Image Compressioncited by 11
  10. 2023On the Choice of Perception Loss Function for Learned Video Compressioncited by 10
  11. 2025Lossy Neural Compression for Geospatial Analytics: A Reviewcited by 10
  12. 2025PICD: Versatile Perceptual Image Compression with Diffusion Renderingcited by 10
  13. 2025CoD: A Diffusion Foundation Model for Image Compressioncited by 9
  14. 2024Region-Adaptive Transform with Segmentation Prior for Image Compressioncited by 8
  15. 2023High Visual-Fidelity Learned Video Compressioncited by 7
  16. 2023The Perception-Robustness Tradeoff in Deterministic Image Restorationcited by 7
  17. 2025Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compressioncited by 7
  18. 2023Conditional Perceptual Quality Preserving Image Compressioncited by 6
  19. 2024Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMscited by 5
  20. 2024High Frequency Matters: Uncertainty Guided Image Compression with Wavelet Diffusioncited by 4
  21. 2024LMM-driven Semantic Image-Text Coding for Ultra Low-bitrate Learned Image Compressioncited by 4
  22. 2025Synonymous Variational Inference for Perceptual Image Compressioncited by 4
  23. 2025Ultra-Low Bitrate Perceptual Image Compression with Shallow Encodercited by 4
  24. 2026Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Texturescited by 4
  25. 2026Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compressioncited by 4
  26. 2026CoD-Lite: Real-Time Diffusion-Based Generative Image Compressioncited by 4
  27. 2024Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated Synthesiscited by 3
  28. 2024Map-Assisted Remote-Sensing Image Compression at Extremely Low Bitratescited by 3
  29. 2025All-in-One Image Compression and Restorationcited by 3
  30. 2024TLIC: Learned Image Compression with ROI-Weighted Distortion and Bit Allocationcited by 2
  31. 2024Low-Latency Neural Stereo Streamingcited by 2
  32. 2024Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimizationcited by 2
  33. 2024Neural Graphics Texture Compression Supporting Random Accesscited by 2
  34. 2024Conditional Hallucinations for Image Compressioncited by 2
  35. 2025Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoffcited by 2
  36. 2025Dataset Distillation as Data Compression: A Rate-Utility Perspectivecited by 2
  37. 2026Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priorscited by 2
  38. 2026What Matters in Practical Learned Image Compressioncited by 2

50 most cited of 79 All 79 (JSON)