mlsanityData to 14 Oct 2026

High-Frequency Enhanced Hybrid Neural Representation for Video Compression

arXiv 2411.06685 ↗First posted 11 Nov 2024cs.CV cs.AI eess.IVcited by 2

Not on the map. Why?

Abstract (arXiv)

Neural Representations for Videos (NeRV) have simplified the video codec process and achieved swift decoding speeds by encoding video content into a neural network, presenting a promising solution for video compression. However, existing work overlooks the crucial issue that videos reconstructed by these methods lack high-frequency details. To address this problem, this paper introduces a High-Frequency Enhanced Hybrid Neural Representation Network. Our method focuses on leveraging high-frequency information to improve the synthesis of fine details by the network. Specifically, we design a wavelet high-frequency encoder that incorporates Wavelet Frequency Decomposer (WFD) blocks to generate high-frequency feature embeddings. Next, we design the High-Frequency Feature Modulation (HFM) block, which leverages the extracted high-frequency embeddings to enhance the fitting process of the decoder. Finally, with the refined Harmonic decoder block and a Dynamic Weighted Frequency Loss, we further reduce the potential loss of high-frequency information. Experiments on the Bunny and UVG datasets demonstrate that our method outperforms other methods, showing notable improvements in detail preservation and compression performance.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 32 of its 47 references that are in the map. First posted on arXiv 11 Nov 2024.

Builds on

32 of 47 references.

References · 32

  1. 2022A ConvNet for the 2020scited by 3,579
  2. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  4. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  5. 2018On the Spectral Bias of Neural Networkscited by 1,341
  6. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  7. 2019Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networkscited by 368
  8. 2018DVC: An End-to-end Deep Video Compression Frameworkcited by 332
  9. 2021NeRV: Neural Representations for Videoscited by 256
  10. 2021COIN: COmpression with Implicit Neural representationscited by 233
  11. 2021Deep Contextual Video Compressioncited by 221
  12. 2023WIRE: Wavelet Implicit Neural Representationscited by 220
20 more
  1. 2020Focal Frequency Loss for Image Reconstruction and Synthesiscited by 206
  2. 2022Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Modelscited by 174
  3. 2021Implicit Neural Representations for Image Compressioncited by 162
  4. 2020Layer-adaptive sparsity for the Magnitude-based Pruningcited by 126
  5. 2022GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimationcited by 86
  6. 2022COIN++: Neural Compression Across Modalitiescited by 82
  7. 2022E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Contextcited by 76
  8. 2021Implicit Neural Video Compressioncited by 52
  9. 2022FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videoscited by 46
  10. 2024IRSAM: Advancing Segment Anything Model for Infrared Small Target Detectioncited by 46
  11. 2021WaveFill: A Wavelet-based Generation Network for Image Inpaintingcited by 44
  12. 2023DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videoscited by 42
  13. 2021On the Out-of-distribution Generalization of Probabilistic Image Modellingcited by 33
  14. 2022PS-NeRV: Patch-wise Stylized Neural Representations for Videoscited by 32
  15. 2024Boosting Neural Representations for Videos with a Conditional Decodercited by 29
  16. 2022WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generationcited by 22
  17. 2022Neural Residual Flow Fields for Efficient Video Representationscited by 16
  18. 2022FreGAN: Exploiting Frequency Components for Training GANs under Limited Datacited by 16
  19. 2023Implicit-explicit Integrated Representations for Multi-view Video Compressioncited by 8
  20. 2023Improved Positional Encoding for Implicit Neural Representation based Compact Data Representationcited by 4

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025FANeRV: Frequency Separation and Augmentation based Neural Representation for Videocited by 1
  2. 2025Towards High-Fidelity Gaussian Splatting with Queried-Convolution Neural Networkscited by 0