mlsanityData to 7 Oct 2026

Neural Video Compression with Diverse Contexts

arXiv 2302.14402 ↗First posted 28 Feb 2023eess.IV cs.CV cs.MMcited by 155

Not on the map. Why?

Abstract (arXiv)

For any video codecs, the coding efficiency highly relies on whether the current signal to be encoded can find the relevant contexts from the previous reconstructed signals. Traditional codec has verified more contexts bring substantial coding gain, but in a time-consuming manner. However, for the emerging neural video codec (NVC), its contexts are still limited, leading to low compression ratio. To boost NVC, this paper proposes increasing the context diversity in both temporal and spatial dimensions. First, we guide the model to learn hierarchical quality patterns across frames, which enriches long-term and yet high-quality temporal contexts. Furthermore, to tap the potential of optical flow-based coding framework, we introduce a group-based offset diversity where the cross-group interaction is proposed for better context mining. In addition, this paper also adopts a quadtree-based partition to increase spatial context diversity when encoding the latent representation in parallel. Experiments show that our codec obtains 23.5% bitrate saving over previous SOTA NVC. Better yet, our codec has surpassed the under-developing next generation traditional codec/ECM in both RGB and YUV420 colorspaces, in terms of PSNR. The codes are at https://github.com/microsoft/DCVC.

Key facts. Cited by 155 papers in the map (data through 7 Oct 2026). Builds on 36 of its 68 references that are in the map. First posted on arXiv 28 Feb 2023.

Builds on

36 of 68 references.

References · 36

  1. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  2. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  3. 2018Variational image compression with a scale hyperpriorcited by 910
  4. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  5. 2017Video Enhancement with Task-Oriented Flowcited by 612
  6. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  7. 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 340
  8. 2018DVC: An End-to-end Deep Video Compression Frameworkcited by 324
  9. 2018TDAN: Temporally Deformable Alignment Network for Video Super-Resolutioncited by 225
  10. 2021Deep Contextual Video Compressioncited by 216
  11. 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 193
  12. 2021FVC: A New Framework towards Deep Video Compression in Feature Spacecited by 149
24 more
  1. 2018Video Compression through Image Interpolationcited by 143
  2. 2022Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compressioncited by 123
  3. 2021Temporal Context Mining for Learned Video Compressioncited by 112
  4. 2020M-LVC: Multiple Frames Prediction for Learned Video Compressioncited by 106
  5. 2022Entroformer: A Transformer-based Entropy Model for Learned Image Compressioncited by 102
  6. 2020Asymmetric Gained Deep Image Compression With Continuous Rate Adaptationcited by 83
  7. 2020Understanding Deformable Alignment in Video Super-Resolutioncited by 78
  8. 2022VCT: A Video Compression Transformercited by 74
  9. 2020Content Adaptive and Error Propagation Aware Deep Video Compressioncited by 72
  10. 2017Parallel Multiscale Autoregressive Density Estimationcited by 71
  11. 2020Causal Contextual Prediction for Learned Image Compressioncited by 70
  12. 2021ELF-VC: Efficient Learned Flexible-Rate Video Codingcited by 68
  13. 2020Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Modelcited by 67
  14. 2022Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Predictioncited by 55
  15. 2021Joint Global and Local Hierarchical Priors for Learned Image Compressioncited by 52
  16. 2023EVC: Towards Real-Time Neural Image Compression with Mask Decaycited by 46
  17. 2022CANF-VC: Conditional Augmented Normalizing Flows for Video Compressioncited by 44
  18. 2020Conditional Entropy Coding for Efficient Video Compressioncited by 42
  19. 2020Learning Accurate Entropy Model with Global Reference for Image Compressioncited by 42
  20. 2020Neural Video Coding using Multiscale Motion Compensation and Spatiotemporal Context Modelcited by 38
  21. 2021Conditional Coding for Flexible Learned Video Compressioncited by 25
  22. 2018Neural Multi-scale Image Compressioncited by 10
  23. 2022Boosting neural video codecs by exploiting hierarchical redundancycited by 5
  24. 2022Towards Hybrid-Optimization Video Codingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 11; 2024: 45; 2025: 59; 2026: 40.

155 papers.

Sort:

By area:

  1. 2024Neural Video Compression with Feature Modulationcited by 115
  2. 2024CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splattingcited by 80
  3. 2025Improving the Diffusability of Autoencoderscited by 74
  4. 2025Towards Practical Real-Time Neural Video Compressioncited by 72
  5. 2023HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representationcited by 70
  6. 2023C3: High-performance and low-complexity neural compression from a single image or videocited by 54
  7. 2024ElasticTok: Adaptive Tokenization for Image and Videocited by 44
  8. 2024USTC-TD: A Test Dataset and Benchmark for Image and Video Coding in 2020scited by 37
  9. 2024NVRC: Neural Video Representation Compressioncited by 29
  10. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 29
  11. 2025One-Step Diffusion-Based Image Compression with Semantic Distillationcited by 23
  12. 2025Generative Latent Coding for Ultra-Low Bitrate Image and Video Compressioncited by 22
38 more
  1. 2024Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compressioncited by 21
  2. 2025Generative Latent Coding for Ultra-Low Bitrate Image Compressioncited by 21
  3. 2024Bi-Directional Deep Contextual Video Compressioncited by 20
  4. 2025DLF: Extreme Image Compression with Dual-generative Latent Fusioncited by 20
  5. 2025Learned Image Compression with Hierarchical Progressive Context Modelingcited by 20
  6. 2024PNVC: Towards Practical INR-based Video Compressioncited by 19
  7. 2023Offline and Online Optical Flow Enhancement for Deep Video Compressioncited by 17
  8. 2025Neural Video Compression with Context Modulationcited by 15
  9. 2024Generative Visual Compression: A Reviewcited by 13
  10. 2024Immersive Video Compression using Implicit Neural Representationscited by 12
  11. 2024Group-aware Parameter-efficient Updating for Content-Adaptive Neural Video Compressioncited by 12
  12. 2023MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Devicecited by 11
  13. 2024Cool-chic video: Learned video coding with 800 parameterscited by 11
  14. 2024SMC++: Masked Learning of Unsupervised Video Semantic Compressioncited by 11
  15. 2024When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Codingcited by 11
  16. 2025Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compressioncited by 10
  17. 2023Towards Real-Time Neural Video Codec for Cross-Platform Application Using Calibration Informationcited by 9
  18. 2024Variable-Rate Learned Image Compression with Multi-Objective Optimization and Quantization-Reconstruction Offsetscited by 9
  19. 2024M3-CVC: Controllable Video Compression with Multimodal Generative Modelscited by 9
  20. 2025GIViC: Generative Implicit Video Compressioncited by 9
  21. 2025DiffVC-OSD: One-Step Diffusion-based Perceptual Neural Video Compression Frameworkcited by 9
  22. 2024Rate-aware Compression for NeRF-based Volumetric Videocited by 8
  23. 2025Augmented Deep Contexts for Spatially Embedded Video Codingcited by 8
  24. 2025BiECVC: Gated Diversification of Bidirectional Contexts for Learned Video Compressioncited by 8
  25. 2025T-GVC: Trajectory-Guided Generative Video Coding at Ultra-Low Bitratescited by 8
  26. 2025Generative Latent Video Compressioncited by 8
  27. 2025Single-step Diffusion-based Video Coding with Semantic-Temporal Guidancecited by 8
  28. 2025GSVC: Efficient Video Representation and Compression Through 2D Gaussian Splattingcited by 7
  29. 2024UCVC: A Unified Contextual Video Compression Framework with Joint P-frame and B-frame Codingcited by 6
  30. 2024Extreme Video Compression with Pre-trained Diffusion Modelscited by 6
  31. 2024Task-Aware Encoder Control for Deep Video Compressioncited by 6
  32. 2024High Efficiency Image Compression for Large Visual-Language Modelscited by 6
  33. 2024Benchmarking Conventional and Learned Video Codecs with a Low-Delay Configurationcited by 6
  34. 2025EHVC: Efficient Hierarchical Reference and Quality Structure for Neural Video Codingcited by 6
  35. 2023Learning Dynamic Point Cloud Compression via Hierarchical Inter-frame Block Matchingcited by 5
  36. 2024Generative Human Video Compression with Multi-granularity Temporal Trajectory Factorizationcited by 5
  37. 20253D Gaussian Splatting Data Compression with Mixture of Priorscited by 5
  38. 2025Conditional Video Generation for High-Efficiency Video Compressioncited by 5

50 most cited of 155 All 155 (JSON)