mlsanityData to 14 Oct 2026

Implicit Neural Video Compression

arXiv 2112.11312 ↗First posted 21 Dec 2021cs.LG cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

We propose a method to compress full-resolution video sequences with implicit neural representations. Each frame is represented as a neural network that maps coordinate positions to pixel values. We use a separate implicit network to modulate the coordinate inputs, which enables efficient motion compensation between frames. Together with a small residual network, this allows us to efficiently compress P-frames relative to the previous frame. We further lower the bitrate by storing the network weights with learned integer quantization. Our method, which we call implicit pixel flow (IPF), offers several simplifications over established neural video codecs: it does not require the receiver to have access to a pretrained neural network, does not use expensive interpolation-based warping operations, and does not require a separate training dataset. We demonstrate the feasibility of neural implicit compression on image and video data.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). Builds on 52 of its 71 references that are in the map. First posted on arXiv 21 Dec 2021.

Builds on

52 of 71 references.

References · 52

  1. 2013Auto-Encoding Variational Bayescited by 4,053
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  4. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  6. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  8. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  9. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  10. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  11. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  12. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
38 more
  1. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  2. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
  3. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  4. 2019Learned Step Size Quantizationcited by 628
  5. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 621
  6. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 521
  7. 2021A White Paper on Neural Network Quantizationcited by 472
  8. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
  9. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  10. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  11. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  12. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 336
  13. 2018DVC: An End-to-end Deep Video Compression Frameworkcited by 332
  14. 2017Lossy Image Compression with Compressive Autoencoderscited by 294
  15. 2020Neural Radiance Flow for 4D View Synthesis and Video Processingcited by 270
  16. 2021NeRV: Neural Representations for Videoscited by 256
  17. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  18. 2021COIN: COmpression with Implicit Neural representationscited by 233
  19. 2020LSQ+: Improving low-bit quantization through learnable offsets and better initializationcited by 189
  20. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 180
  21. 2021Implicit Neural Representations for Image Compressioncited by 162
  22. 2021FVC: A New Framework towards Deep Video Compression in Feature Spacecited by 153
  23. 2019NASA: Neural Articulated Shape Approximationcited by 149
  24. 2018Video Compression through Image Interpolationcited by 143
  25. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
  26. 2019Learning to Infer Implicit Surfaces without 3D Supervisioncited by 103
  27. 2019Video Compression With Rate-Distortion Autoencoderscited by 97
  28. 2020Bayesian Bits: Unifying Quantization and Pruningcited by 94
  29. 2018Learned Video Compressioncited by 89
  30. 2019And the Bit Goes Down: Revisiting the Quantization of Neural Networkscited by 78
  31. 2021Overfitting for Fun and Profit: Instance-Adaptive Data Compressioncited by 38
  32. 2020Feedback Recurrent Autoencoder for Video Compressioncited by 30
  33. 2021Extending Neural P-frame Codecs for B-frame Codingcited by 30
  34. 2019Learned Video Compression via Joint Spatial-Temporal Correlation Explorationcited by 28
  35. 2019Learning Image and Video Compression through Spatial-Temporal Energy Compactioncited by 27
  36. 2018Learning for Video Compressioncited by 26
  37. 2018Deep Generative Video Compressioncited by 23
  38. 2021Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Setcited by 18

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 17; 2023: 10; 2024: 14; 2025: 6; 2026: 5.

52 papers.

Sort:

By area:

  1. 2022From data to functa: Your data point is a function and you can treat it like onecited by 187
  2. 2022Variable Bitrate Neural Fieldscited by 117
  3. 2023Implicit Neural Representation for Cooperative Low-light Image Enhancementcited by 92
  4. 2022COIN++: Neural Compression Across Modalitiescited by 82
  5. 2022E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Contextcited by 76
  6. 2022Unified Implicit Neural Stylizationcited by 67
  7. 2023NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functionscited by 65
  8. 2023Deep Learning on Implicit Neural Representations of Shapescited by 63
  9. 2022NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modelingcited by 51
  10. 2022Signal Processing for Implicit Neural Representationscited by 46
  11. 2022FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videoscited by 46
  12. 2023Towards Scalable Neural Representation for Diverse Videoscited by 37
38 more
  1. 2022Scalable Neural Video Representations with Learnable Positional Featurescited by 29
  2. 2022Neural Fourier Filter Bankcited by 29
  3. 2024Boosting Neural Representations for Videos with a Conditional Decodercited by 29
  4. 2024NVRC: Neural Video Representation Compressioncited by 29
  5. 2022Meta-Learning Sparse Compression Networkscited by 22
  6. 2022On Quantizing Implicit Neural Representationscited by 20
  7. 2022MobileCodec: Neural Inter-frame Video Compression on Mobile Devicescited by 19
  8. 2024PNVC: Towards Practical INR-based Video Compressioncited by 19
  9. 2022Neural Residual Flow Fields for Efficient Video Representationscited by 16
  10. 2024Learning Transferable Features for Implicit Neural Representationscited by 14
  11. 2023Regularize implicit neural representation by itselfcited by 13
  12. 2023Implicit-explicit Integrated Representations for Multi-view Video Compressioncited by 8
  13. 2023Scene Matters: Model-based Deep Video Compressioncited by 6
  14. 2023Deep Learning on Object-centric 3D Neural Fieldscited by 5
  15. 2022Frame Interpolation for Dynamic Scenes with Implicit Flow Encodingcited by 4
  16. 2022Rethinking Implicit Neural Representations for Vision Learnerscited by 4
  17. 2023MoEC: Mixture of Experts Implicit Neural Compressioncited by 4
  18. 2025UAR-NVC: A Unified AutoRegressive Framework for Memory-Efficient Neural Video Compressioncited by 3
  19. 2026Enhanced Neural Video Representation Compression Across Extreme Complexity and Quality Scalescited by 3
  20. 2023Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural Representationcited by 2
  21. 2024Robustly overfitting latents for flexible neural image compressioncited by 2
  22. 2024Low-Latency Neural Stereo Streamingcited by 2
  23. 2024Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimizationcited by 2
  24. 2024Towards the Spectral bias Alleviation by Normalizations in Coordinate Networkscited by 2
  25. 2024Predicting the Encoding Error of SIRENscited by 2
  26. 2024High-Frequency Enhanced Hybrid Neural Representation for Video Compressioncited by 2
  27. 2025CANeRV: Content Adaptive Neural Representation for Video Compressioncited by 2
  28. 2022Optical Flow Regularization of Implicit Neural Representations for Video Frame Interpolationcited by 1
  29. 2024Implicit Neural Representation For Accurate CFD Flow Field Predictioncited by 1
  30. 2024Implicit Neural Compression of Point Cloudscited by 1
  31. 2025Efficient Implicit Neural Compression of Point Clouds via Learnable Activation in Latent Spacecited by 1
  32. 2026TeCoNeRV: Leveraging Temporal Coherence for Compressible Neural Representations for Videoscited by 1
  33. 2024Distributed Radiance Fields for Edge Video Compression and Metaverse Integration in Autonomous Drivingcited by 0
  34. 2024MNeRV: A Multilayer Neural Representation for Videoscited by 0
  35. 2025INRet: A General Framework for Accurate Retrieval of INRs for Shapescited by 0
  36. 2025NeRV-Diffusion: Diffuse Implicit Neural Representations for Video Synthesiscited by 0
  37. 2025In Situ Training of Implicit Neural Compressors for Scientific Simulations via Sketch-Based Regularizationcited by 0
  38. 2026What Cohort INRs Encode and Where to Freeze Themcited by 0

50 most cited of 52 All 52 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models
  2. 2023HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation
  3. 2024Extreme Compression of Adaptive Neural Images
  4. 2025GIViC: Generative Implicit Video Compression
  5. 2025A Lightweight Model for Perceptual Image Compression via Implicit Priors
  6. 2026NeuralLVC: Neural Lossless Video Compression via Masked Diffusion with Temporal Conditioning
  7. 2022A Coding Framework and Benchmark towards Low-Bitrate Video Understanding
  8. 2023SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representations