mlsanityData to 14 Oct 2026

COIN++: Neural Compression Across Modalities

arXiv 2201.12904 ↗First posted 30 Jan 2022cs.LG cs.CV eess.IVcited by 82

Not on the map. Why?

Abstract (arXiv)

Neural compression algorithms are typically based on autoencoders that require specialized encoder and decoder architectures for different data modalities. In this paper, we propose COIN++, a neural compression framework that seamlessly handles a wide range of data modalities. Our approach is based on converting data to implicit neural representations, i.e. neural functions that map coordinates (such as pixel locations) to features (such as RGB values). Then, instead of storing the weights of the implicit neural representation directly, we store modulations applied to a meta-learned base network as a compressed code for the data. We further quantize and entropy code these modulations, leading to large compression gains while reducing encoding time by two orders of magnitude compared to baselines. We empirically demonstrate the feasibility of our method by compressing various data modalities, from images and audio to medical and climate data.

Key facts. Cited by 82 papers in the map (data through 14 Oct 2026). Builds on 53 of its 81 references that are in the map. First posted on arXiv 30 Jan 2022.

Builds on

53 of 81 references.

References · 53

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  6. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  8. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  9. 2018Variational image compression with a scale hyperpriorcited by 935
  10. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  11. 2021SoundStream: An End-to-End Neural Audio Codeccited by 771
  12. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
38 more
  1. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  2. 2016End-to-end Optimized Image Compressioncited by 696
  3. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  4. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 664
  5. 2019Learned Step Size Quantizationcited by 628
  6. 2017Video Enhancement with Task-Oriented Flowcited by 619
  7. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 590
  8. 2019Meta-Learning with Implicit Gradientscited by 525
  9. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 521
  10. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  11. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 470
  12. 2020High-Fidelity Generative Image Compressioncited by 338
  13. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 336
  14. 2018DVC: An End-to-end Deep Video Compression Frameworkcited by 332
  15. 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 301
  16. 2017Lossy Image Compression with Compressive Autoencoderscited by 294
  17. 2020CompressAI: a PyTorch library and evaluation platform for end-to-end compression researchcited by 276
  18. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
  19. 2021NeRV: Neural Representations for Videoscited by 256
  20. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 242
  21. 2021COIN: COmpression with Implicit Neural representationscited by 233
  22. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 219
  23. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  24. 2021Implicit Neural Representations for Image Compressioncited by 162
  25. 2018Context-adaptive Entropy Model for End-to-end Optimized Image Compressioncited by 143
  26. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
  27. 2020Adversarial Generation of Continuous Imagescited by 135
  28. 2021Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPscited by 135
  29. 2018Conditional Probability Models for Deep Image Compressioncited by 133
  30. 2018LPCNet: Improving Neural Speech Synthesis Through Linear Predictioncited by 110
  31. 2020Image Generators with Conditionally-Independent Pixel Synthesiscited by 106
  32. 2021Enhanced Invertible Encoding for Learned Image Compressioncited by 105
  33. 2021Generative Models as Distributions of Functionscited by 89
  34. 2019Image and Video Compression with Neural Networks: A Reviewcited by 86
  35. 2021Compressive Neural Representations of Volumetric Scalar Fieldscited by 64
  36. 2021Implicit Neural Video Compressioncited by 52
  37. 2021Meta-Learning Sparse Implicit Neural Representationscited by 48
  38. 2017Wavenet based low rate speech codingcited by 33

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 13; 2024: 28; 2025: 24; 2026: 13.

82 papers.

Sort:

By area:

  1. 2024GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splattingcited by 99
  2. 2023NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functionscited by 65
  3. 2023C3: High-performance and low-complexity neural compression from a single image or videocited by 55
  4. 2023Continuous-Time Functional Diffusion Processescited by 39
  5. 2022Compressing multidimensional weather and climate data into neural networkscited by 31
  6. 2022Neural Fourier Filter Bankcited by 29
  7. 2023Compression with Bayesian Implicit Neural Representationscited by 25
  8. 2024Latent Modulated Function for Computational Optimal Continuous Image Representationcited by 21
  9. 2023Compact Neural Graphics Primitives with Learned Hash Probingcited by 19
  10. 2024Learning Transferable Features for Implicit Neural Representationscited by 14
  11. 2024Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Datacited by 13
  12. 2024Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein Distortioncited by 13
38 more
  1. 2023Versatile Neural Processes for Learning Implicit Neural Representationscited by 11
  2. 2024Fast Training of Sinusoidal Neural Fields via Scaling Initializationcited by 11
  3. 2025Meta-INR: Efficient Encoding of Volumetric Data via Meta-Learning Implicit Neural Representationcited by 11
  4. 2025Lossy Neural Compression for Geospatial Analytics: A Reviewcited by 10
  5. 2023Latent assimilation with implicit neural representations for unknown dynamicscited by 9
  6. 2023RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representationscited by 9
  7. 2024ASMR: Activation-sharing Multi-resolution Coordinate Networks For Efficient Inferencecited by 9
  8. 2025Optimizing Rank for High-Fidelity Implicit Neural Representationscited by 8
  9. 2023In Search of a Data Transformation That Accelerates Neural Field Trainingcited by 7
  10. 2025MedFuncta: A Unified Framework for Learning Efficient Medical Neural Fieldscited by 7
  11. 2025F-INR: Functional Tensor Decomposition for Implicit Neural Representationscited by 7
  12. 2024Towards Croppable Implicit Neural Representationscited by 5
  13. 2025Towards Lossless Implicit Neural Representation via Bit Plane Decompositioncited by 5
  14. 2025A Physics-Informed Meta-Learning Framework for the Continuous Solution of Parametric PDEs on Arbitrary Geometriescited by 5
  15. 2022SINCO: A Novel structural regularizer for image compression using implicit neural representationscited by 4
  16. 2023Coordinate-Aware Modulation for Neural Fieldscited by 4
  17. 2024Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinementcited by 4
  18. 2024Hybrid Neural Representations for Spherical Datacited by 3
  19. 2024NERV++: An Enhanced Implicit Neural Video Representationcited by 3
  20. 2024Encoding Semantic Priors into the Weights of Implicit Neural Representationcited by 3
  21. 2024Neural Video Representation for Redundancy Reduction and Consistency Preservationcited by 3
  22. 2024Query Quantized Neural SLAMcited by 3
  23. 2025UAR-NVC: A Unified AutoRegressive Framework for Memory-Efficient Neural Video Compressioncited by 3
  24. 2025Transforming Weather Data from Pixel to Latent Spacecited by 3
  25. 2025SINR: Sparsity Driven Compressed Implicit Neural Representationscited by 3
  26. 2026SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representationcited by 3
  27. 2022Learning Neural Implicit Representations with Surface Signal Parameterizationscited by 2
  28. 2023Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural Representationcited by 2
  29. 2024Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimizationcited by 2
  30. 2024Conv-INR: Convolutional Implicit Neural Representation for Multimodal Visual Signalscited by 2
  31. 2024Uncertainty modeling for fine-tuned implicit functionscited by 2
  32. 2024Towards the Spectral bias Alleviation by Normalizations in Coordinate Networkscited by 2
  33. 2024Predicting the Encoding Error of SIRENscited by 2
  34. 2024High-Frequency Enhanced Hybrid Neural Representation for Video Compressioncited by 2
  35. 2025Efficient Neural Video Representation with Temporally Coherent Modulationcited by 2
  36. 2025Fourier-Modulated Implicit Neural Representation for Multispectral Satellite Image Compressioncited by 2
  37. 2025COLI: A Hierarchical Efficient Compressor for Large Imagescited by 2
  38. 2025VidFuncta: Towards Generalizable Neural Representations for Ultrasound Videoscited by 2

50 most cited of 82 All 82 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022An Introduction to Neural Data Compression
  2. 2025Ultra-Efficient Decoding for End-to-End Neural Compression and Reconstruction
  3. 2023End-to-End Neural Network Compression via fracℓ1ℓ2 Regularized Latency Surrogates
  4. 2026SoftBinary Coding: A New Information-Theoretic Neural Compression Paradigm
  5. 2025Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding
  6. 2024Unicorn: Unified Neural Image Compression with One Number Reconstruction
  7. 2023Joint Hierarchical Priors and Adaptive Spatial Resolution for Efficient Neural Image Compression
  8. 2024"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach