mlsanityData to 14 Oct 2026

Generative Adversarial Networks for Extreme Learned Image Compression

arXiv 1804.02958 ↗First posted 9 Apr 2018cs.CV cs.LGcited by 219

Not on the map. Why?

Cited by 30 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a learned image compression system based on GANs, operating at extremely low bitrates. Our proposed framework combines an encoder, decoder/generator and a multi-scale discriminator, which we train jointly for a generative learned compression objective. The model synthesizes details it cannot afford to store, obtaining visually pleasing results at bitrates where previous methods fail and show strong artifacts. Furthermore, if a semantic label map of the original image is available, our method can fully synthesize unimportant regions in the decoded image such as streets and trees from the label map, proportionally reducing the storage cost. A user study confirms that for low bitrates, our approach is preferred to state-of-the-art methods, even when they use more than double the bits.

Key facts. Cited by 219 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 39; 2022: 41; 2023: 40; 2024: 39; 2025: 29; 2026: 31.

219 papers.

Sort:

By area:

  1. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 640
  2. 2023Finite Scalar Quantization: VQ-VAE Made Simplecited by 440
  3. 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 202
  4. 2022Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communicationscited by 175
  5. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 170
  6. 2021Implicit Neural Representations for Image Compressioncited by 162
  7. 2021FVC: A New Framework towards Deep Video Compression in Feature Spacecited by 153
  8. 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 147
  9. 2021Enhanced Invertible Encoding for Learned Image Compressioncited by 105
  10. 2023Towards image compression with perfect realism at ultra-low bitratescited by 103
  11. 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Modelscited by 94
  12. 2021Semantic Communications: Principles and Challengescited by 91
38 more
  1. 2022Lossy Compression with Gaussian Diffusioncited by 90
  2. 2022COIN++: Neural Compression Across Modalitiescited by 82
  3. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 80
  4. 2022An Introduction to Neural Data Compressioncited by 79
  5. 2021ELF-VC: Efficient Learned Flexible-Rate Video Codingcited by 69
  6. 2023Text + Sketch: Image Compression at Ultra Low Ratescited by 67
  7. 2024Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Priorcited by 60
  8. 2021Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transformcited by 58
  9. 2022Generative Joint Source-Channel Coding for Semantic Image Transmissioncited by 58
  10. 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 56
  11. 2023High-Fidelity Image Compression with Score-based Generative Modelscited by 54
  12. 2021Lossy Compression for Lossless Predictioncited by 52
  13. 2021Universal Rate-Distortion-Perception Representations for Lossy Compressioncited by 47
  14. 2021Perceptual Learned Video Compression with Recurrent Conditional GANcited by 41
  15. 2023Generative Semantic Communication: Diffusion Models Beyond Bit Recoverycited by 41
  16. 2021Slimmable Compressive Autoencoders for Practical Neural Image Compressioncited by 39
  17. 2021Neural Video Compression using GANs for Detail Synthesis and Propagationcited by 36
  18. 2022Towards Semantic Communications: Deep Learning-Based Image Semantic Codingcited by 36
  19. 2024Lossy Image Compression with Foundation Diffusion Modelscited by 36
  20. 2023A Residual Diffusion Model for High Perceptual Quality Codec Augmentationcited by 35
  21. 2022Image Compression with Product Quantized Masked Image Modelingcited by 33
  22. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 33
  23. 2022Extreme Generative Image Compression by Learning Text Embedding from Diffusion Modelscited by 31
  24. 2021A coding theorem for the rate-distortion-perception functioncited by 30
  25. 2023Extreme Image Compression using Fine-tuned VQGANscited by 29
  26. 2021On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Frameworkcited by 27
  27. 2025One-Step Diffusion-Based Image Compression with Semantic Distillationcited by 26
  28. 2021DPICT: Deep Progressive Image Compression Using Trit-Planescited by 25
  29. 2023Compression with Bayesian Implicit Neural Representationscited by 25
  30. 2025Generative Latent Coding for Ultra-Low Bitrate Image and Video Compressioncited by 25
  31. 2024RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusioncited by 23
  32. 2025Generative Latent Coding for Ultra-Low Bitrate Image Compressioncited by 23
  33. 2023Modality-Agnostic Variational Compression of Implicit Neural Representationscited by 22
  34. 2022The Rate-Distortion-Perception Tradeoff: The Role of Common Randomnesscited by 21
  35. 2025DLF: Extreme Image Compression with Dual-generative Latent Fusioncited by 21
  36. 2022Flexible Neural Image Compression via Code Editingcited by 20
  37. 2023LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compressioncited by 19
  38. 2024PerCo (SD): Open Perceptual Compressioncited by 18

50 most cited of 219 All 219 (JSON)