mlsanityData to 13 Oct 2026

PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videos

arXiv 2404.08921 ↗First posted 13 Apr 2024cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

The primary focus of Neural Representation for Videos (NeRV) is to effectively model its spatiotemporal consistency. However, current NeRV systems often face a significant issue of spatial inconsistency, leading to decreased perceptual quality. To address this issue, we introduce the Pyramidal Neural Representation for Videos (PNeRV), which is built on a multi-scale information connection and comprises a lightweight rescaling operator, Kronecker Fully-connected layer (KFc), and a Benign Selective Memory (BSM) mechanism. The KFc, inspired by the tensor decomposition of the vanilla Fully-connected layer, facilitates low-cost rescaling and global correlation modeling. BSM merges high-level features with granular ones adaptively. Furthermore, we provide an analysis based on the Universal Approximation Theory of the NeRV system and validate the effectiveness of the proposed PNeRV.We conducted comprehensive experiments to demonstrate that PNeRV surpasses the performance of contemporary NeRV models, achieving the best results in video regression on UVG and DAVIS under various metrics (PSNR, SSIM, LPIPS, and FVD). Compared to vanilla NeRV, PNeRV achieves a +4.49 dB gain in PSNR and a 231% increase in FVD on UVG, along with a +3.28 dB PSNR and 634% FVD increase on DAVIS.

Key facts. Cited by 10 papers in the map (data through 13 Oct 2026). Builds on 56 of its 76 references that are in the map. First posted on arXiv 13 Apr 2024.

Builds on

56 of 76 references.

References · 56

  1. 2017Attention Is All You Needcited by 60,106
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,952
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,656
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,777
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,231
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,111
  7. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,082
  8. 2022Generative Adversarial Networkscited by 5,614
  9. 2016Feature Pyramid Networks for Object Detectioncited by 5,027
  10. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,712
  11. 2022A ConvNet for the 2020scited by 3,563
  12. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,352
38 more
  1. 2017Non-local Neural Networkscited by 2,291
  2. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,225
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,183
  4. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,961
  5. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,610
  6. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,581
  7. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,522
  8. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,217
  9. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  10. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,202
  11. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,129
  12. 2018Path Aggregation Network for Instance Segmentationcited by 798
  13. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 720
  14. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  15. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  16. 2019Deep Double Descent: Where Bigger Models and More Data Hurtcited by 670
  17. 2020Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuningcited by 665
  18. 2017The Perception-Distortion Tradeoffcited by 585
  19. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  20. 2018DVC: An End-to-end Deep Video Compression Frameworkcited by 329
  21. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 311
  22. 2021NeRV: Neural Representations for Videoscited by 256
  23. 2017High-dimensional dynamics of generalization error in neural networkscited by 241
  24. 2021COIN: COmpression with Implicit Neural representationscited by 233
  25. 2023Language Modeling Is Compressioncited by 225
  26. 2021Deep Contextual Video Compressioncited by 219
  27. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 216
  28. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 208
  29. 2021FVC: A New Framework towards Deep Video Compression in Feature Spacecited by 153
  30. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  31. 2017Approximating Continuous Functions by ReLU Nets of Minimal Widthcited by 120
  32. 2022Is Attention All That NeRF Needs?cited by 113
  33. 2020M-LVC: Multiple Frames Prediction for Learned Video Compressioncited by 107
  34. 2017Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activationscited by 104
  35. 2023HNeRV: A Hybrid Neural Representation for Videoscited by 100
  36. 2020Minimum Width for Universal Approximationcited by 92
  37. 2018ResNet with one-neuron hidden layers is a Universal Approximatorcited by 78
  38. 2022E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Contextcited by 76

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 4.

10 papers.

  1. 2024Neural Video Representation for Redundancy Reduction and Consistency Preservationcited by 3
  2. 2025How to Design and Train Your Implicit Neural Representation for Video Compressioncited by 3
  3. 2025Tree-NeRV: A Tree-Structured Neural Representation for Efficient Non-Uniform Video Encodingcited by 2
  4. 2025SR-NeRV: Improving Embedding Efficiency of Neural Video Representation via Super-Resolutioncited by 2
  5. 2025GSVR: 2D Gaussian-based Video Representation for 800+ FPS with Hybrid Deformation Fieldcited by 2
  6. 2026Implicit Neural Representation Facilitates Unified Universal Vision Encodingcited by 1
  7. 2026CWRNN-INVR: A Coupled WarpRNN based Implicit Neural Video Representationcited by 1
  8. 2025Structure-Preserving Patch Decoding for Efficient Neural Video Representationcited by 0
  9. 2026OmniStyle-INR: Universal and Multimodal Style Transfer for INRscited by 0
  10. 2026Resolution-Flexible Decoding for Hybrid Neural Video Representationscited by 0