mlsanityData to 13 Oct 2026

In Search of a Data Transformation That Accelerates Neural Field Training

arXiv 2311.17094 ↗First posted 28 Nov 2023cs.LG cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Neural field is an emerging paradigm in data representation that trains a neural network to approximate the given signal. A key obstacle that prevents its widespread adoption is the encoding speed-generating neural fields requires an overfitting of a neural network, which can take a significant number of SGD steps to reach the desired fidelity level. In this paper, we delve into the impacts of data transformations on the speed of neural field training, specifically focusing on how permuting pixel locations affect the convergence speed of SGD. Counterintuitively, we find that randomly permuting the pixel locations can considerably accelerate the training. To explain this phenomenon, we examine the neural field training through the lens of PSNR curves, loss landscapes, and error patterns. Our analyses suggest that the random pixel permutations remove the easy-to-fit patterns, which facilitate easy optimization in the early stage but hinder capturing fine details of the signal.

Key facts. Cited by 7 papers in the map (data through 13 Oct 2026). Builds on 40 of its 47 references that are in the map. First posted on arXiv 28 Nov 2023.

Builds on

40 of 47 references.

References · 40

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,712
  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. 2016Understanding deep learning requires rethinking generalizationcited by 1,666
  5. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,610
  6. 2018On the Spectral Bias of Neural Networkscited by 1,329
  7. 2017Visualizing the Loss Landscape of Neural Netscited by 1,129
  8. 2020Neural Sparse Voxel Fieldscited by 959
  9. 2017A Closer Look at Memorization in Deep Networkscited by 939
  10. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  11. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  12. 2021Neural Fields in Visual Computing and Beyondcited by 539
28 more
  1. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  2. 2014In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learningcited by 340
  3. 2017Implicit Regularization in Matrix Factorizationcited by 321
  4. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 241
  5. 2021COIN: COmpression with Implicit Neural representationscited by 233
  6. 2023WIRE: Wavelet Implicit Neural Representationscited by 220
  7. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  8. 2018Measuring the Effects of Data Parallelism on Neural Network Trainingcited by 193
  9. 2014Qualitatively characterizing neural network optimization problemscited by 187
  10. 2022From data to functa: Your data point is a function and you can treat it like onecited by 186
  11. 2018Deep learning generalizes because the parameter-function map is biased towards simple functionscited by 180
  12. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 142
  13. 2019The Convergence Rate of Neural Networks for Learned Functions of Different Frequenciescited by 135
  14. 2020Implicit Regularization in Deep Learning May Not Be Explainable by Normscited by 119
  15. 2021A Structured Dictionary Perspective on Implicit Neural Representationscited by 100
  16. 2022COIN++: Neural Compression Across Modalitiescited by 82
  17. 2019A Fine-Grained Spectral Perspective on Neural Networkscited by 68
  18. 2023Deep Learning on Implicit Neural Representations of Shapescited by 63
  19. 2020What Do Neural Networks Learn When Trained With Random Labels?cited by 58
  20. 2022COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codeccited by 51
  21. 2022Signal Processing for Implicit Neural Representationscited by 46
  22. 2021Joint Implicit Image Function for Guided Depth Super-Resolutioncited by 31
  23. 2022Generalised Implicit Neural Representationscited by 31
  24. 2022Scalable Neural Video Representations with Learnable Positional Featurescited by 29
  25. 2023Modality-Agnostic Variational Compression of Implicit Neural Representationscited by 22
  26. 2021Implicit Neural Representation Learning for Hyperspectral Image Super-Resolutioncited by 17
  27. 2023Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesiscited by 13
  28. 2014Compression, Restoration, Re-sampling, Compressive Sensing: Fast Transforms in Digital Imagingcited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 1.

7 papers.

  1. 2024Fast Training of Sinusoidal Neural Fields via Scaling Initializationcited by 11
  2. 2025Stochastic Preconditioning for Neural Field Optimizationcited by 8
  3. 2024EVOS: Efficient Implicit Neural Training via EVOlutionary Selectorcited by 6
  4. 2024Enhancing Implicit Neural Representations via Symmetric Power Transformationcited by 4
  5. 2025NTK-Guided Implicit Neural Teachingcited by 2
  6. 2025Enhancing Robustness of Implicit Neural Representations Against Weight Perturbationscited by 1
  7. 2026CARA: Collision-Aware Resolution Adaptation for Multiresolution Hash Encoding Based Image Fittingcited by 0