mlsanityData to 7 Oct 2026

Channel-wise Autoregressive Entropy Models for Learned Image Compression

arXiv 2007.08739 ↗First posted 17 Jul 2020eess.IV cs.CV cs.ITcited by 255

Not on the map. Why?

Abstract (arXiv)

In learning-based approaches to image compression, codecs are developed by optimizing a computational model to minimize a rate-distortion objective. Currently, the most effective learned image codecs take the form of an entropy-constrained autoencoder with an entropy model that uses both forward and backward adaptation. Forward adaptation makes use of side information and can be efficiently integrated into a deep neural network. In contrast, backward adaptation typically makes predictions based on the causal context of each symbol, which requires serial processing that prevents efficient GPU / TPU utilization. We introduce two enhancements, channel-conditioning and latent residual prediction, that lead to network architectures with better rate-distortion performance than existing context-adaptive models while minimizing serial processing. Empirically, we see an average rate savings of 6.7% on the Kodak image set and 11.4% on the Tecnick image set compared to a context-adaptive baseline model. At low bit rates, where the improvements are most effective, our model saves up to 18% over the baseline and outperforms hand-engineered codecs like BPG by up to 25%.

Key facts. Cited by 255 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 38; 2023: 49; 2024: 60; 2025: 58; 2026: 30.

255 papers.

Sort:

By area:

  1. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  2. 2023Learned Image Compression with Mixed Transformer-CNN Architecturescited by 205
  3. 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 193
  4. 2022Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communicationscited by 166
  5. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  6. 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 141
  7. 2021Enhanced Invertible Encoding for Learned Image Compressioncited by 102
  8. 2022Entroformer: A Transformer-based Entropy Model for Learned Image Compressioncited by 102
  9. 2023Towards image compression with perfect realism at ultra-low bitratescited by 99
  10. 2022MLIC: Multi-Reference Entropy Model for Learned Image Compressioncited by 80
  11. 2024CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splattingcited by 80
  12. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
38 more
  1. 2022An Introduction to Neural Data Compressioncited by 78
  2. 2022VCT: A Video Compression Transformercited by 74
  3. 2021Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transformcited by 56
  4. 2023MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compressioncited by 56
  5. 2023Frequency-Aware Transformer for Learned Image Compressioncited by 56
  6. 2024Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Priorcited by 56
  7. 2022Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Predictioncited by 55
  8. 2023High-Fidelity Image Compression with Score-based Generative Modelscited by 53
  9. 2021Joint Global and Local Hierarchical Priors for Learned Image Compressioncited by 52
  10. 2021Lossy Compression for Lossless Predictioncited by 51
  11. 2023EVC: Towards Real-Time Neural Image Compression with Mask Decaycited by 46
  12. 2022Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compressioncited by 42
  13. 2021Slimmable Compressive Autoencoders for Practical Neural Image Compressioncited by 38
  14. 2021Neural Video Compression using GANs for Detail Synthesis and Propagationcited by 35
  15. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 32
  16. 2022Image Compression with Product Quantized Masked Image Modelingcited by 32
  17. 2021Supervised Compression for Resource-Constrained Edge Computing Systemscited by 31
  18. 2022Image Coding for Machines with Omnipotent Feature Learningcited by 31
  19. 2021Extending Neural P-frame Codecs for B-frame Codingcited by 30
  20. 2025Learned Image Compression with Dictionary-based Entropy Modelcited by 29
  21. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 29
  22. 2021End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compressioncited by 28
  23. 2024Idempotence and Perceptual Image Compressioncited by 27
  24. 2024Image Compression for Machine and Human Vision with Spatial-Frequency Adaptationcited by 26
  25. 2023Compression with Bayesian Implicit Neural Representationscited by 25
  26. 2021Progressive Neural Image Compression with Nested Quantization and Latent Orderingcited by 24
  27. 2023Computationally-Efficient Neural Image Compression with Shallow Decoderscited by 22
  28. 2024CRA5: Extreme Compression of ERA5 for Portable Global Climate and Weather Research via an Efficient Variational Transformercited by 22
  29. 2022Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compressioncited by 21
  30. 2023Context-Based Trit-Plane Coding for Progressive Image Compressioncited by 21
  31. 2024Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compressioncited by 21
  32. 2024RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusioncited by 21
  33. 2025Learned Image Compression with Hierarchical Progressive Context Modelingcited by 20
  34. 2022Flexible Neural Image Compression via Code Editingcited by 19
  35. 2023LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compressioncited by 19
  36. 2024PNVC: Towards Practical INR-based Video Compressioncited by 19
  37. 2024Causal Context Adjustment Loss for Learned Image Compressioncited by 19
  38. 2023Raw Image Reconstruction with Learned Compact Metadatacited by 18

50 most cited of 255 All 255 (JSON)