mlsanityData to 7 Oct 2026

Nonlinear Transform Coding

arXiv 2007.03034 ↗First posted 6 Jul 2020cs.IT eess.IV math.ITcited by 132

Not on the map. Why?

Abstract (arXiv)

We review a class of methods that can be collected under the name nonlinear transform coding (NTC), which over the past few years have become competitive with the best linear transform codecs for images, and have superseded them in terms of rate--distortion performance under established perceptual quality metrics such as MS-SSIM. We assess the empirical rate--distortion performance of NTC with the help of simple example sources, for which the optimal performance of a vector quantizer is easier to estimate than with natural data sources. To this end, we introduce a novel variant of entropy-constrained vector quantization. We provide an analysis of various forms of stochastic optimization techniques for NTC models; review architectures of transforms based on artificial neural networks, as well as learned entropy models; and provide a direct comparison of a number of methods to parameterize the rate--distortion trade-off of nonlinear transforms, introducing a simplified one.

Key facts. Cited by 132 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 23; 2023: 25; 2024: 26; 2025: 28; 2026: 14.

132 papers.

Sort:

By area:

  1. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  2. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  3. 2022Variable Bitrate Neural Fieldscited by 116
  4. 2024Image and Video Tokenization with Binary Spherical Quantizationcited by 110
  5. 2022Lossy Compression with Gaussian Diffusioncited by 87
  6. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 79
  7. 2022An Introduction to Neural Data Compressioncited by 78
  8. 2022VCT: A Video Compression Transformercited by 74
  9. 2021Nonlinear Transform Source-Channel Coding for Semantic Communicationscited by 73
  10. 2023Text + Sketch: Image Compression at Ultra Low Ratescited by 63
  11. 2023MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compressioncited by 56
  12. 2021Joint Global and Local Hierarchical Priors for Learned Image Compressioncited by 52
38 more
  1. 2021Lossy Compression for Lossless Predictioncited by 51
  2. 2022Wireless Deep Video Semantic Transmissioncited by 49
  3. 2022Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compressioncited by 42
  4. 2024Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariancecited by 42
  5. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 32
  6. 2022Neural Data-Dependent Transform for Learned Image Compressioncited by 29
  7. 2021On the advantages of stochastic encoderscited by 28
  8. 2021End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video Compressioncited by 28
  9. 2024Image Compression for Machine and Human Vision with Spatial-Frequency Adaptationcited by 26
  10. 2024Latency-Aware Generative Semantic Communications with Pre-Trained Diffusion Modelscited by 25
  11. 2025Compression of 3D Gaussian Splatting with Optimized Feature Planes and Standard Video Codecscited by 24
  12. 2023Random-Access Neural Compression of Material Texturescited by 23
  13. 2023Computationally-Efficient Neural Image Compression with Shallow Decoderscited by 22
  14. 2025Linear Attention Modeling for Learned Image Compressioncited by 22
  15. 2021LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networkscited by 19
  16. 2023Joint Task and Data Oriented Semantic Communications: A Deep Separate Source-channel Coding Schemecited by 19
  17. 2025Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inferencecited by 18
  18. 2022High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregationcited by 16
  19. 2024NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representationcited by 16
  20. 2022MobileCodec: Neural Inter-frame Video Compression on Mobile Devicescited by 15
  21. 2023M2T: Masking Transformers Twice for Faster Decodingcited by 14
  22. 2023NVTC: Nonlinear Vector Transform Codingcited by 14
  23. 2021Neural Distributed Source Codingcited by 13
  24. 2021Towards Empirical Sandwich Bounds on the Rate-Distortion Functioncited by 13
  25. 2023Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compressioncited by 13
  26. 2023FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computingcited by 12
  27. 2023Semantically Structured Image Compression via Irregular Group-Based Decouplingcited by 12
  28. 2025Image Quality Assessment: From Human to Machine Preferencecited by 12
  29. 2024What makes an image realistic?cited by 10
  30. 2025Lossy Neural Compression for Geospatial Analytics: A Reviewcited by 10
  31. 2021Insights from Generative Modeling for Neural Video Compressioncited by 9
  32. 2022Neural Estimation of the Rate-Distortion Function With Applications to Operational Source Codingcited by 9
  33. 2023RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representationscited by 9
  34. 2024Variable-Rate Learned Image Compression with Multi-Objective Optimization and Quantization-Reconstruction Offsetscited by 9
  35. 2021Self-Organized Variational Autoencoders (Self-VAE) for Learned Image Compressioncited by 8
  36. 2022Attention-Based Generative Neural Image Compression on Solar Dynamics Observatorycited by 8
  37. 2022Toward Adaptive Semantic Communications: Efficient Data Transmission via Online Learned Nonlinear Transform Source-Channel Codingcited by 8
  38. 2023ECRF: Entropy-Constrained Neural Radiance Fields Compression with Frequency Domain Optimizationcited by 8

50 most cited of 132 All 132 (JSON)