mlsanityData to 14 Oct 2026

NeRV: Neural Representations for Videos

arXiv 2110.13903 ↗First posted 26 Oct 2021cs.CV eess.IVcited by 256

Not on the map. Why?

Abstract (arXiv)

We propose a novel neural representation for videos (NeRV) which encodes videos in neural networks. Unlike conventional representations that treat videos as frame sequences, we represent videos as neural networks taking frame index as input. Given a frame index, NeRV outputs the corresponding RGB image. Video encoding in NeRV is simply fitting a neural network to video frames and decoding process is a simple feedforward operation. As an image-wise implicit representation, NeRV output the whole image and shows great efficiency compared to pixel-wise implicit representation, improving the encoding speed by 25x to 70x, the decoding speed by 38x to 132x, while achieving better video quality. With such a representation, we can treat videos as neural networks, simplifying several video-related tasks. For example, conventional video compression methods are restricted by a long and complex pipeline, specifically designed for the task. In contrast, with NeRV, we can use any neural network compression method as a proxy for video compression, and achieve comparable performance to traditional frame-based video compression approaches (H.264, HEVC etc). Besides compression, we demonstrate the generalization of NeRV for video denoising. The source code and pre-trained model can be found at https://github.com/haochen-rye/NeRV.git.

Key facts. Cited by 256 papers in the map (data through 14 Oct 2026). Builds on 44 of its 63 references that are in the map. First posted on arXiv 26 Oct 2021.

Builds on

44 of 63 references.

References · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  6. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  7. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  8. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  9. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  10. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  11. 2018On the Spectral Bias of Neural Networkscited by 1,341
  12. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
32 more
  1. 2016Group Equivariant Convolutional Networkscited by 1,165
  2. 2017Deep Image Priorcited by 1,098
  3. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  4. 2020Convolutional Occupancy Networkscited by 761
  5. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  6. 2016Learning Structured Sparsity in Deep Neural Networkscited by 541
  7. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 521
  8. 2013Do Deep Nets Really Need to be Deep?cited by 474
  9. 2015Deep Learning with Limited Numerical Precisioncited by 376
  10. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  11. 2018DVC: An End-to-end Deep Video Compression Frameworkcited by 332
  12. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  13. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 306
  14. 2018Model compression via distillation and quantizationcited by 289
  15. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 284
  16. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  17. 2021COIN: COmpression with Implicit Neural representationscited by 233
  18. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  19. 2016A guide to convolution arithmetic for deep learningcited by 185
  20. 2018Training Deep Neural Networks with 8-bit Floating Point Numberscited by 164
  21. 2018Video Compression through Image Interpolationcited by 143
  22. 2018Scalable Methods for 8-bit Training of Neural Networkscited by 142
  23. 2016Exploiting Cyclic Symmetry in Convolutional Neural Networkscited by 91
  24. 2020Learning for Video Compression with Hierarchical Quality and Recurrent Enhancementcited by 90
  25. 2018Learned Video Compressioncited by 89
  26. 2016Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Unitscited by 86
  27. 2020Adaptive Gradient Quantization for Data-Parallel SGDcited by 45
  28. 2020Conditional Entropy Coding for Efficient Video Compressioncited by 42
  29. 2020Hierarchical Autoregressive Modeling for Neural Video Compressioncited by 28
  30. 2019Learning Image and Video Compression through Spatial-Temporal Energy Compactioncited by 27
  31. 2019Local Deep Implicit Functions for 3D Shapecited by 18
  32. 2016Doubly Convolutional Neural Networkscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 37; 2023: 44; 2024: 67; 2025: 60; 2026: 45.

256 papers.

Sort:

By area:

  1. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 301
  2. 2023EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingScited by 196
  3. 2022From data to functa: Your data point is a function and you can treat it like onecited by 187
  4. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  5. 2021Implicit Neural Representations for Image Compressioncited by 162
  6. 2022Is Attention All That NeRF Needs?cited by 113
  7. 2022EpiGRAF: Rethinking training of 3D GANscited by 108
  8. 2023HNeRV: A Hybrid Neural Representation for Videoscited by 100
  9. 2024GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splattingcited by 99
  10. 2023Implicit Neural Representation for Cooperative Low-light Image Enhancementcited by 92
  11. 2023Implicit Neural Representation in Medical Imaging: A Comparative Surveycited by 90
  12. 2022COIN++: Neural Compression Across Modalitiescited by 82
38 more
  1. 2023FINER: Flexible spectral-bias tuning in Implicit NEural Representation by Variable-periodic Activation Functionscited by 78
  2. 2022E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Contextcited by 76
  3. 2022Continuous PDE Dynamics Forecasting with Implicit Neural Representationscited by 73
  4. 2023HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representationcited by 71
  5. 2022Unified Implicit Neural Stylizationcited by 67
  6. 2023NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functionscited by 65
  7. 2023Spatial Functa: Scaling Functa to ImageNet Classification and Generationcited by 57
  8. 2023C3: High-performance and low-complexity neural compression from a single image or videocited by 55
  9. 2024Bidirectional Multi-Scale Implicit Neural Representations for Image Derainingcited by 54
  10. 2021Implicit Neural Video Compressioncited by 52
  11. 2022NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modelingcited by 51
  12. 2022Signal Processing for Implicit Neural Representationscited by 46
  13. 2022FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videoscited by 46
  14. 2023DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videoscited by 42
  15. 2022Generalizable Implicit Neural Representations via Instance Pattern Composerscited by 39
  16. 2023Towards Scalable Neural Representation for Diverse Videoscited by 37
  17. 2024USTC-TD: A Test Dataset and Benchmark for Image and Video Coding in 2020scited by 37
  18. 2023PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervisioncited by 36
  19. 2022PS-NeRV: Patch-wise Stylized Neural Representations for Videoscited by 32
  20. 2022Compressing multidimensional weather and climate data into neural networkscited by 31
  21. 2023SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representationscited by 31
  22. 2022DINER: Disorder-Invariant Implicit Neural Representationcited by 30
  23. 2022Scalable Neural Video Representations with Learnable Positional Featurescited by 29
  24. 2024Boosting Neural Representations for Videos with a Conditional Decodercited by 29
  25. 2024NVRC: Neural Video Representation Compressioncited by 29
  26. 2024V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussianscited by 29
  27. 2023Blind Video Deflickering by Neural Filtering with a Flawed Atlascited by 27
  28. 2023Disorder-invariant Implicit Neural Representationcited by 27
  29. 2023Compression with Bayesian Implicit Neural Representationscited by 25
  30. 2024DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codescited by 25
  31. 2022Meta-Learning Sparse Compression Networkscited by 22
  32. 2024Latent Modulated Function for Computational Optimal Continuous Image Representationcited by 21
  33. 2022MINER: Multiscale Implicit Neural Representationscited by 20
  34. 2022On Quantizing Implicit Neural Representationscited by 20
  35. 2023iNVS: Repurposing Diffusion Inpainters for Novel View Synthesiscited by 20
  36. 2023GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understandingcited by 20
  37. 2024PNVC: Towards Practical INR-based Video Compressioncited by 19
  38. 2025Instant GaussianImage: A Generalizable and Self-Adaptive Image Representation via 2D Gaussian Splattingcited by 18

50 most cited of 256 All 256 (JSON)