mlsanityData to 14 Oct 2026

Real-Time Adaptive Image Compression

arXiv 1705.05823 ↗First posted 16 May 2017stat.ML cs.CV cs.LGcited by 130

Not on the map. Why?

Abstract (arXiv)

We present a machine learning-based approach to lossy image compression which outperforms all existing codecs, while running in real-time. Our algorithm typically produces files 2.5 times smaller than JPEG and JPEG 2000, 2 times smaller than WebP, and 1.7 times smaller than BPG on datasets of generic images across all quality levels. At the same time, our codec is designed to be lightweight and deployable: for example, it can encode or decode the Kodak dataset in around 10ms per image on GPU. Our architecture is an autoencoder featuring pyramidal analysis, an adaptive coding module, and regularization of the expected codelength. We also supplement our approach with adversarial training specialized towards use in a compression setting: this enables us to produce visually pleasing reconstructions for very low bitrates.

Key facts. Cited by 130 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 30; 2022: 36; 2023: 23; 2024: 20; 2025: 12; 2026: 9.

130 papers.

Sort:

By area:

  1. 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 202
  2. 2022Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communicationscited by 175
  3. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 170
  4. 2021Enhanced Invertible Encoding for Learned Image Compressioncited by 105
  5. 2021Semantic Communications: Principles and Challengescited by 91
  6. 2022MLIC: Multi-Reference Entropy Model for Learned Image Compressioncited by 84
  7. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 80
  8. 2022An Introduction to Neural Data Compressioncited by 79
  9. 2021ELF-VC: Efficient Learned Flexible-Rate Video Codingcited by 69
  10. 2021Image-to-image Translation via Hierarchical Style Disentanglementcited by 63
  11. 2024Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Priorcited by 60
  12. 2021Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transformcited by 58
38 more
  1. 2023High-Fidelity Image Compression with Score-based Generative Modelscited by 54
  2. 2021Soft then Hard: Rethinking the Quantization in Neural Image Compressioncited by 51
  3. 2021Slimmable Compressive Autoencoders for Practical Neural Image Compressioncited by 39
  4. 2021Neural Video Compression using GANs for Detail Synthesis and Propagationcited by 36
  5. 2022Towards Semantic Communications: Deep Learning-Based Image Semantic Codingcited by 36
  6. 2021Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modulescited by 35
  7. 2023A Residual Diffusion Model for High Perceptual Quality Codec Augmentationcited by 35
  8. 2022Image Compression with Product Quantized Masked Image Modelingcited by 33
  9. 2022Extreme Generative Image Compression by Learning Text Embedding from Diffusion Modelscited by 31
  10. 2021Extending Neural P-frame Codecs for B-frame Codingcited by 30
  11. 2021A coding theorem for the rate-distortion-perception functioncited by 30
  12. 2024MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Modelcited by 30
  13. 2023Extreme Image Compression using Fine-tuned VQGANscited by 29
  14. 2024Idempotence and Perceptual Image Compressioncited by 29
  15. 2021On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Frameworkcited by 27
  16. 2021DPICT: Deep Progressive Image Compression Using Trit-Planescited by 25
  17. 2023Computationally-Efficient Neural Image Compression with Shallow Decoderscited by 23
  18. 2023Random-Access Neural Compression of Material Texturescited by 23
  19. 2024LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Modelscited by 22
  20. 2022The Rate-Distortion-Perception Tradeoff: The Role of Common Randomnesscited by 21
  21. 2022MobileCodec: Neural Inter-frame Video Compression on Mobile Devicescited by 19
  22. 2023LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compressioncited by 19
  23. 2022Selective compression learning of latent representations for variable-rate image compressioncited by 17
  24. 2024Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Modelcited by 17
  25. 2021Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeletoncited by 16
  26. 2021Learning Scalable ℓ_∞-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compressioncited by 16
  27. 2023Multi-Modality Deep Network for Extreme Learned Image Compressioncited by 16
  28. 2024Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptationcited by 16
  29. 2022Neural Distributed Image Compression with Cross-Attention Feature Alignmentcited by 15
  30. 2022Invertible Rescaling Network and Its Extensionscited by 15
  31. 2023EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentationcited by 14
  32. 2022Learning-Driven Lossy Image Compression; A Comprehensive Surveycited by 13
  33. 2022Optimally Controllable Perceptual Lossy Compressioncited by 13
  34. 2023ProgDTD: Progressive Learned Image Compression with Double-Tail-Drop Trainingcited by 13
  35. 2023MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Devicecited by 13
  36. 2024Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decodercited by 13
  37. 2021LC-FDNet: Learned Lossless Image Compression with Frequency Decomposition Networkcited by 12
  38. 2022Perceptual Learned Source-Channel Coding for High-Fidelity Image Semantic Transmissioncited by 12

50 most cited of 130 All 130 (JSON)