mlsanityData to 7 Oct 2026

Deep Generative Models for Distribution-Preserving Lossy Compression

arXiv 1805.11057 ↗First posted 28 May 2018cs.LG stat.MLcited by 59

Not on the map. Why?

Abstract (arXiv)

We propose and study the problem of distribution-preserving lossy compression. Motivated by recent advances in extreme image compression which allow to maintain artifact-free reconstructions even at very low bitrates, we propose to optimize the rate-distortion tradeoff under the constraint that the reconstructed samples follow the distribution of the training data. The resulting compression system recovers both ends of the spectrum: On one hand, at zero bitrate it learns a generative model of the data, and at high enough bitrates it achieves perfect reconstruction. Furthermore, for intermediate bitrates it smoothly interpolates between learning a generative model of the training data and perfectly reconstructing the training samples. We study several methods to approximately solve the proposed optimization problem, including a novel combination of Wasserstein GAN and Wasserstein Autoencoder, and present an extensive theoretical and empirical characterization of the proposed compression systems.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 10; 2023: 12; 2024: 8; 2025: 8; 2026: 4.

59 papers.

Sort:

By area:

  1. 2023Finite Scalar Quantization: VQ-VAE Made Simplecited by 425
  2. 2022Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communicationscited by 166
  3. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  4. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  5. 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Modelscited by 90
  6. 2022Lossy Compression with Gaussian Diffusioncited by 87
  7. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  8. 2021Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transformcited by 56
  9. 2022Generative Joint Source-Channel Coding for Semantic Image Transmissioncited by 55
  10. 2021Universal Rate-Distortion-Perception Representations for Lossy Compressioncited by 46
  11. 2021Slimmable Compressive Autoencoders for Practical Neural Image Compressioncited by 38
  12. 2021Neural Video Compression using GANs for Detail Synthesis and Propagationcited by 35
38 more
  1. 2023A Residual Diffusion Model for High Perceptual Quality Codec Augmentationcited by 33
  2. 2022Extreme Generative Image Compression by Learning Text Embedding from Diffusion Modelscited by 30
  3. 2021On the advantages of stochastic encoderscited by 28
  4. 2021On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Frameworkcited by 27
  5. 2024Idempotence and Perceptual Image Compressioncited by 27
  6. 2021DPICT: Deep Progressive Image Compression Using Trit-Planescited by 25
  7. 2022The Rate-Distortion-Perception Tradeoff: The Role of Common Randomnesscited by 21
  8. 2024PerCo (SD): Open Perceptual Compressioncited by 16
  9. 2024Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptationcited by 15
  10. 2023M2T: Masking Transformers Twice for Faster Decodingcited by 14
  11. 2023Multi-Modality Deep Network for Extreme Learned Image Compressioncited by 14
  12. 2022Optimally Controllable Perceptual Lossy Compressioncited by 13
  13. 2023ProgDTD: Progressive Learned Image Compression with Double-Tail-Drop Trainingcited by 13
  14. 2023EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentationcited by 13
  15. 2022Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utilitycited by 12
  16. 2023A Review of Change of Variable Formulas for Generative Modelingcited by 12
  17. 2024PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videoscited by 10
  18. 2025PICD: Versatile Perceptual Image Compression with Diffusion Renderingcited by 10
  19. 2023ECSIC: Epipolar Cross Attention for Stereo Image Compressioncited by 8
  20. 2023Wasserstein Distortion: Unifying Fidelity and Realismcited by 8
  21. 2021Pragmatic Image Compression for Human-in-the-Loop Decision-Makingcited by 7
  22. 2023Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformerscited by 7
  23. 2021Rate Distortion Characteristic Modeling for Neural Image Compressioncited by 6
  24. 2023Conditional Perceptual Quality Preserving Image Compressioncited by 6
  25. 2024Deep Learning in Physical Layer: Review on Data Driven End-to-End Communication Systems and their Enabling Semantic Applicationscited by 6
  26. 2021Lossless Compression with Latent Variable Modelscited by 4
  27. 2021MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domainscited by 4
  28. 2022Video Coding Using Learned Latent GAN Compressioncited by 4
  29. 2024A Rate-Distortion-Classification Approach for Lossy Image Compressioncited by 3
  30. 2025Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compressioncited by 3
  31. 2024Wavelet-Like Transform-Based Technology in Response to the Call for Proposals on Neural Network-Based Image Codingcited by 2
  32. 2024Conditional Hallucinations for Image Compressioncited by 2
  33. 2025Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoffcited by 2
  34. 2021Principal Bit Analysis: Autoencoding with Schur-Concave Losscited by 1
  35. 2021PixelPyramids: Exact Inference Models from Lossless Image Pyramidscited by 1
  36. 2025Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Imagescited by 1
  37. 2025Generative Image Compression by Estimating Gradients of the Rate-variable Feature Distributioncited by 1
  38. 2026Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and LLM Reconstructioncited by 1

50 most cited of 59 All 59 (JSON)