mlsanityData to 7 Oct 2026

Checkerboard Context Model for Efficient Learned Image Compression

arXiv 2103.15306 ↗First posted 29 Mar 2021eess.IV cs.CVcited by 193

Not on the map. Why?

Abstract (arXiv)

For learned image compression, the autoregressive context model is proved effective in improving the rate-distortion (RD) performance. Because it helps remove spatial redundancies among latent representations. However, the decoding process must be done in a strict scan order, which breaks the parallelization. We propose a parallelizable checkerboard context model (CCM) to solve the problem. Our two-pass checkerboard context calculation eliminates such limitations on spatial locations by re-organizing the decoding order. Speeding up the decoding process more than 40 times in our experiments, it achieves significantly improved computational efficiency with almost the same rate-distortion performance. To the best of our knowledge, this is the first exploration on parallelization-friendly spatial context model for learned image compression.

Key facts. Cited by 193 papers in the map (data through 7 Oct 2026). Builds on 19 of its 38 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

19 of 38 references.

References · 19

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2018Variational image compression with a scale hyperpriorcited by 910
  3. 2016End-to-end Optimized Image Compressioncited by 673
  4. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  5. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  6. 2017Lossy Image Compression with Compressive Autoencoderscited by 289
  7. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 255
  8. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  9. 2016Full Resolution Image Compression with Recurrent Neural Networkscited by 170
  10. 2018Context-adaptive Entropy Model for End-to-end Optimized Image Compressioncited by 138
  11. 2017Real-Time Adaptive Image Compressioncited by 127
  12. 2019Variable Rate Deep Image Compression With a Conditional Autoencodercited by 109
7 more
  1. 2017Learning Convolutional Networks for Content-weighted Image Compressioncited by 73
  2. 2019Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compressioncited by 33
  3. 2019Computationally Efficient Neural Image Compressioncited by 31
  4. 2018Efficient Nonlinear Transforms for Lossy Image Compressioncited by 20
  5. 2018Image-Dependent Local Entropy Models for Learned Image Compressioncited by 12
  6. 2019Multi-scale and Context-adaptive Entropy Model for Image Compressioncited by 9
  7. 2017Learning to Inpaint for Image Compressioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 24; 2023: 37; 2024: 46; 2025: 47; 2026: 32.

193 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. 2024HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compressioncited by 202
  4. 2023Neural Video Compression with Diverse Contextscited by 155
  5. 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 141
  6. 2022Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compressioncited by 123
  7. 2022Entroformer: A Transformer-based Entropy Model for Learned Image Compressioncited by 102
  8. 2022MLIC: Multi-Reference Entropy Model for Learned Image Compressioncited by 80
  9. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  10. 2023MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compressioncited by 56
  11. 2024Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Priorcited by 56
  12. 2023C3: High-performance and low-complexity neural compression from a single image or videocited by 54
38 more
  1. 2021Joint Global and Local Hierarchical Priors for Learned Image Compressioncited by 52
  2. 2025HAC++: Towards 100X Compression of 3D Gaussian Splattingcited by 52
  3. 2023EVC: Towards Real-Time Neural Image Compression with Mask Decaycited by 46
  4. 2022Unified Multivariate Gaussian Mixture for Efficient Neural Image Compressioncited by 43
  5. 2022Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compressioncited by 42
  6. 2021Perceptual Learned Video Compression with Recurrent Conditional GANcited by 38
  7. 2021Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modulescited by 33
  8. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 32
  9. 2022Image Compression with Product Quantized Masked Image Modelingcited by 32
  10. 2024HEMGS: A Hybrid Entropy Model for 3D Gaussian Splatting Data Compressioncited by 31
  11. 2024How Far Can We Compress Instant-NGP-Based NeRF?cited by 30
  12. 2024NVRC: Neural Video Representation Compressioncited by 29
  13. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 29
  14. 2023Compression with Bayesian Implicit Neural Representationscited by 25
  15. 20223DAC: Learning Attribute Compression for Point Cloudscited by 22
  16. 2023Computationally-Efficient Neural Image Compression with Shallow Decoderscited by 22
  17. 2022Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compressioncited by 21
  18. 2023Context-Based Trit-Plane Coding for Progressive Image Compressioncited by 21
  19. 2024Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compressioncited by 21
  20. 2024RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusioncited by 21
  21. 2025Generative Latent Coding for Ultra-Low Bitrate Image Compressioncited by 21
  22. 2025Learned Image Compression with Hierarchical Progressive Context Modelingcited by 20
  23. 2022Flexible Neural Image Compression via Code Editingcited by 19
  24. 2023LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compressioncited by 19
  25. 2024Causal Context Adjustment Loss for Learned Image Compressioncited by 19
  26. 2023Raw Image Reconstruction with Learned Compact Metadatacited by 18
  27. 2025MambaIC: State Space Models for High-Performance Learned Image Compressioncited by 18
  28. 2025Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inferencecited by 18
  29. 2022High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregationcited by 16
  30. 2024Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Modelcited by 16
  31. 2025Large Language Model for Lossless Image Compression with Visual Promptscited by 15
  32. 2025Neural Video Compression with Context Modulationcited by 15
  33. 2022Advancing Learned Video Compression with In-loop Frame Predictioncited by 14
  34. 2023M2T: Masking Transformers Twice for Faster Decodingcited by 14
  35. 2023LDMIC: Learning-based Distributed Multi-view Image Codingcited by 13
  36. 2023Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compressioncited by 13
  37. 2023End-to-End Learnable Multi-Scale Feature Compression for VCMcited by 13
  38. 2021LC-FDNet: Learned Lossless Image Compression with Frequency Decomposition Networkcited by 12

50 most cited of 193 All 193 (JSON)