mlsanityData to 7 Oct 2026

COIN: COmpression with Implicit Neural representations

arXiv 2103.03123 ↗First posted 3 Mar 2021eess.IV cs.CV cs.LGcited by 232

Not on the map. Why?

Abstract (arXiv)

We propose a new simple approach for image compression: instead of storing the RGB values for each pixel of an image, we store the weights of a neural network overfitted to the image. Specifically, to encode an image, we fit it with an MLP which maps pixel locations to RGB values. We then quantize and store the weights of this MLP as a code for the image. To decode the image, we simply evaluate the MLP at every pixel location. We found that this simple approach outperforms JPEG at low bit-rates, even without entropy coding or learning a distribution over weights. While our framework is not yet competitive with state of the art compression methods, we show that it has various attractive properties which could make it a viable alternative to other neural data compression approaches.

Key facts. Cited by 232 papers in the map (data through 7 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 3 Mar 2021.

Builds on

31 of 45 references.

References · 31

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  3. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  5. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  6. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2018Variational image compression with a scale hyperpriorcited by 910
  9. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  10. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  11. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  12. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
19 more
  1. 2020CompressAI: a PyTorch library and evaluation platform for end-to-end compression researchcited by 271
  2. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 240
  3. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  4. 2018Context-adaptive Entropy Model for End-to-end Optimized Image Compressioncited by 138
  5. 2019The Convergence Rate of Neural Networks for Learned Functions of Different Frequenciescited by 134
  6. 2018Inference Suboptimality in Variational Autoencoderscited by 131
  7. 2017Bayesian Compression for Deep Learningcited by 116
  8. 2017Soft Weight-Sharing for Neural Network Compressioncited by 99
  9. 2018Iterative Amortized Inferencecited by 93
  10. 2020Bayesian Bits: Unifying Quantization and Pruningcited by 93
  11. 2021Generative Models as Distributions of Functionscited by 89
  12. 2018Semi-Amortized Variational Autoencoderscited by 83
  13. 2020Improving Inference for Neural Image Compressioncited by 81
  14. 2018Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameterscited by 56
  15. 2020Equivariant Neural Renderingcited by 47
  16. 2018RenderNet: A deep convolutional network for differentiable rendering from 3D shapescited by 42
  17. 2019Content Adaptive Optimization for Neural Image Compressioncited by 40
  18. 2021Overfitting for Fun and Profit: Instance-Adaptive Data Compressioncited by 38
  19. 2017On the challenges of learning with inference networks on sparse, high-dimensional datacited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 38; 2023: 48; 2024: 51; 2025: 43; 2026: 41.

232 papers.

Sort:

By area:

  1. 2021Neural Fields in Visual Computing and Beyondcited by 539
  2. 2021NeRV: Neural Representations for Videoscited by 255
  3. 2023EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingScited by 191
  4. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  5. 2022From data to functa: Your data point is a function and you can treat it like onecited by 183
  6. 2021Implicit Neural Representations for Image Compressioncited by 161
  7. 2022Variable Bitrate Neural Fieldscited by 116
  8. 2021A Structured Dictionary Perspective on Implicit Neural Representationscited by 100
  9. 2023HNeRV: A Hybrid Neural Representation for Videoscited by 100
  10. 2024GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splattingcited by 97
  11. 2022COIN++: Neural Compression Across Modalitiescited by 81
  12. 2023FINER: Flexible spectral-bias tuning in Implicit NEural Representation by Variable-periodic Activation Functionscited by 77
38 more
  1. 2023HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representationcited by 70
  2. 2022Unified Implicit Neural Stylizationcited by 67
  3. 2023Deep Learning on Implicit Neural Representations of Shapescited by 62
  4. 2023Spatial Functa: Scaling Functa to ImageNet Classification and Generationcited by 55
  5. 2023C3: High-performance and low-complexity neural compression from a single image or videocited by 54
  6. 2021Implicit Neural Video Compressioncited by 52
  7. 2022NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modelingcited by 50
  8. 2021Meta-Learning Sparse Implicit Neural Representationscited by 48
  9. 2022Signal Processing for Implicit Neural Representationscited by 46
  10. 2022FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videoscited by 46
  11. 2022Generalizable Implicit Neural Representations via Instance Pattern Composerscited by 38
  12. 2023Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictionscited by 38
  13. 2023Towards Scalable Neural Representation for Diverse Videoscited by 37
  14. 2024Image-GS: Content-Adaptive Image Representation via 2D Gaussianscited by 34
  15. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
  16. 2022Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondencecited by 32
  17. 2022Image Compression with Product Quantized Masked Image Modelingcited by 32
  18. 2021High Quality Segmentation for Ultra High-resolution Imagescited by 31
  19. 2022Compressing multidimensional weather and climate data into neural networkscited by 31
  20. 2023SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representationscited by 31
  21. 2022Scalable Neural Video Representations with Learnable Positional Featurescited by 29
  22. 2022Neural Fourier Filter Bankcited by 29
  23. 2024NVRC: Neural Video Representation Compressioncited by 29
  24. 2023Compression with Bayesian Implicit Neural Representationscited by 25
  25. 2025Locality-aware Gaussian Compression for Fast and High-quality Renderingcited by 24
  26. 2023Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fieldscited by 23
  27. 2022Meta-Learning Sparse Compression Networkscited by 22
  28. 2023Modality-Agnostic Variational Compression of Implicit Neural Representationscited by 22
  29. 2023Polynomial Neural Fields for Subband Decomposition and Manipulationcited by 22
  30. 2022CNeRV: Content-adaptive Neural Representation for Visual Datacited by 21
  31. 2022On Quantizing Implicit Neural Representationscited by 20
  32. 2022Transform Once: Efficient Operator Learning in Frequency Domaincited by 20
  33. 2022UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomographycited by 19
  34. 2022Medical Image Registration via Neural Fieldscited by 19
  35. 2023Compact Neural Graphics Primitives with Learned Hash Probingcited by 19
  36. 2024PNVC: Towards Practical INR-based Video Compressioncited by 19
  37. 2021Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Setcited by 18
  38. 2024Tuning the Frequencies: Robust Training for Sinusoidal Neural Networkscited by 18

50 most cited of 232 All 232 (JSON)