mlsanityData to 7 Oct 2026

Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models

arXiv 2301.11189 ↗First posted 26 Jan 2023eess.IV cs.AI cs.CVcited by 90

Not on the map. Why?

Cited by 35 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Lossy image compression aims to represent images in as few bits as possible while maintaining fidelity to the original. Theoretical results indicate that optimizing distortion metrics such as PSNR or MS-SSIM necessarily leads to a discrepancy in the statistics of original images from those of reconstructions, in particular at low bitrates, often manifested by the blurring of the compressed images. Previous work has leveraged adversarial discriminators to improve statistical fidelity. Yet these binary discriminators adopted from generative modeling tasks may not be ideal for image compression. In this paper, we introduce a non-binary discriminator that is conditioned on quantized local image representations obtained via VQ-VAE autoencoders. Our evaluations on the CLIC2020, DIV2K and Kodak datasets show that our discriminator is more effective for jointly optimizing distortion (e.g., PSNR) and statistical fidelity (e.g., FID) than the PatchGAN of the state-of-the-art HiFiC model. On CLIC2020, we obtain the same FID as HiFiC with 30-40% fewer bits.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). Builds on 46 of its 76 references that are in the map. First posted on arXiv 26 Jan 2023.

Builds on

46 of 76 references.

References · 46

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2017Neural Discrete Representation Learningcited by 4,650
  7. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  9. 2014Conditional Generative Adversarial Netscited by 2,152
  10. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  11. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  12. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
34 more
  1. 2018Demystifying MMD GANscited by 1,268
  2. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  3. 2016Deep Variational Information Bottleneckcited by 915
  4. 2018Variational image compression with a scale hyperpriorcited by 910
  5. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  6. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  7. 2016End-to-end Optimized Image Compressioncited by 673
  8. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  9. 2017The Perception-Distortion Tradeoffcited by 582
  10. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  11. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
  12. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  13. 2021XCiT: Cross-Covariance Image Transformerscited by 335
  14. 2020High-Fidelity Generative Image Compressioncited by 331
  15. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  16. 2017Lossy Image Compression with Compressive Autoencoderscited by 289
  17. 2020CompressAI: a PyTorch library and evaluation platform for end-to-end compression researchcited by 271
  18. 2017Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesiscited by 215
  19. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  20. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
  21. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 207
  22. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  23. 2022Lossy Compression with Gaussian Diffusioncited by 87
  24. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  25. 2018Deep Generative Models for Distribution-Preserving Lossy Compressioncited by 59
  26. 2018Towards Image Understanding from Deep Compression without Decodingcited by 52
  27. 2021Lossy Compression for Lossless Predictioncited by 51
  28. 2020End-to-end Learning of Compressible Featurescited by 43
  29. 2021Neural Video Compression using GANs for Detail Synthesis and Propagationcited by 35
  30. 2023A Residual Diffusion Model for High Perceptual Quality Codec Augmentationcited by 33
  31. 2022Image Compression with Product Quantized Masked Image Modelingcited by 32
  32. 2021Supervised Compression for Resource-Constrained Edge Computing Systemscited by 31
  33. 2020An Unsupervised Information-Theoretic Perceptual Quality Metriccited by 28
  34. 2021On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Frameworkcited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 13; 2025: 43; 2026: 30.

90 papers.

Sort:

By area:

  1. 2023Towards image compression with perfect realism at ultra-low bitratescited by 99
  2. 2024Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Priorcited by 56
  3. 2024Lossy Image Compression with Foundation Diffusion Modelscited by 34
  4. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 29
  5. 2024Idempotence and Perceptual Image Compressioncited by 27
  6. 2025Compressed Image Generation with Denoising Diffusion Codebook Modelscited by 24
  7. 2025Lossy Compression with Pretrained Diffusion Modelscited by 23
  8. 2025One-Step Diffusion-Based Image Compression with Semantic Distillationcited by 23
  9. 2025Generative Latent Coding for Ultra-Low Bitrate Image and Video Compressioncited by 22
  10. 2024RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusioncited by 21
  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. 2025DLF: Extreme Image Compression with Dual-generative Latent Fusioncited by 20
  2. 2025Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusioncited by 17
  3. 2024Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptationcited by 15
  4. 2023EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentationcited by 13
  5. 2024Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decodercited by 11
  6. 2025PICD: Versatile Perceptual Image Compression with Diffusion Renderingcited by 10
  7. 2025CoD: A Diffusion Foundation Model for Image Compressioncited by 9
  8. 2025T-GVC: Trajectory-Guided Generative Video Coding at Ultra-Low Bitratescited by 8
  9. 2025Generative Latent Video Compressioncited by 8
  10. 2025Single-step Diffusion-based Video Coding with Semantic-Temporal Guidancecited by 8
  11. 2025Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compressioncited by 7
  12. 2024PSC: Posterior Sampling-Based Compressioncited by 5
  13. 2025PRISM-DP: Spatial Pose-based Observations for Diffusion-Policies via Segmentation, Mesh Generation, and Pose Trackingcited by 5
  14. 2024High Frequency Matters: Uncertainty Guided Image Compression with Wavelet Diffusioncited by 4
  15. 2025HDCompression: Hybrid-Diffusion Image Compression for Ultra-Low Bitratescited by 4
  16. 2025Extremely low-bitrate Image Compression Semantically Disentangled by LMMs from a Human Perception Perspectivecited by 4
  17. 2025Synonymous Variational Inference for Perceptual Image Compressioncited by 4
  18. 2025Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compressioncited by 4
  19. 2025Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Priorcited by 4
  20. 2025Ultra-Low Bitrate Perceptual Image Compression with Shallow Encodercited by 4
  21. 2026Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Texturescited by 4
  22. 2026Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compressioncited by 4
  23. 2026CoD-Lite: Real-Time Diffusion-Based Generative Image Compressioncited by 4
  24. 2024Map-Assisted Remote-Sensing Image Compression at Extremely Low Bitratescited by 3
  25. 2025Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compressioncited by 3
  26. 2026DiT-IC: Aligned Diffusion Transformer for Efficient Image Compressioncited by 3
  27. 2024Low-Latency Neural Stereo Streamingcited by 2
  28. 2024Neural Graphics Texture Compression Supporting Random Accesscited by 2
  29. 2025Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoffcited by 2
  30. 2025Why Compress What You Can Generate? When GPT-4o Generation Ushers in Image Compression Fieldscited by 2
  31. 2025Single-step Diffusion for Image Compression at Ultra-Low Bitratescited by 2
  32. 2025Noise is All You Need: Solving Linear Inverse Problems by Noise Combination Sampling with Diffusion Modelscited by 2
  33. 2026Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unificationcited by 2
  34. 2026ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantizationcited by 2
  35. 2026Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priorscited by 2
  36. 2026Drop-In Perceptual Optimization for 3D Gaussian Splattingcited by 2
  37. 2024Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compressioncited by 1
  38. 2025Hierarchical Semantic Compression for Consistent Image Semantic Restorationcited by 1

50 most cited of 90 All 90 (JSON)