mlsanityData to 14 Oct 2026

INR-Bench: A Unified Benchmark for Implicit Neural Representations in Multi-Domain Regression and Reconstruction

arXiv 2510.10188 ↗First posted 11 Oct 2025cs.LG cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Implicit Neural Representations (INRs) have gained success in various signal processing tasks due to their advantages of continuity and infinite resolution. However, the factors influencing their effectiveness and limitations remain underexplored. To better understand these factors, we leverage insights from Neural Tangent Kernel (NTK) theory to analyze how model architectures (classic MLP and emerging KAN), positional encoding, and nonlinear primitives affect the response to signals of varying frequencies. Building on this analysis, we introduce INR-Bench, the first comprehensive benchmark specifically designed for multimodal INR tasks. It includes 56 variants of Coordinate-MLP models (featuring 4 types of positional encoding and 14 activation functions) and 22 Coordinate-KAN models with distinct basis functions, evaluated across 9 implicit multimodal tasks. These tasks cover both forward and inverse problems, offering a robust platform to highlight the strengths and limitations of different neural models, thereby establishing a solid foundation for future research. The code and dataset are available at https://github.com/lif314/INR-Bench.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 36 of its 49 references that are in the map. First posted on arXiv 11 Oct 2025.

Builds on

36 of 49 references.

References · 36

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
  4. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  7. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  8. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  9. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  10. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  11. 2019Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descentcited by 738
  12. 2024KAN: Kolmogorov-Arnold Networkscited by 649
24 more
  1. 2019Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networkscited by 566
  2. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  3. 2018SDR - half-baked or well done?cited by 423
  4. 2023BakedSDF: Meshing Neural SDFs for Real-Time View Synthesiscited by 221
  5. 2023WIRE: Wavelet Implicit Neural Representationscited by 220
  6. 2020Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networkscited by 200
  7. 2019On the Inductive Bias of Neural Tangent Kernelscited by 177
  8. 2021NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstructioncited by 146
  9. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 143
  10. 2020Frequency Bias in Neural Networks for Input of Non-Uniform Densitycited by 140
  11. 2021Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPscited by 135
  12. 2024Kolmogorov-Arnold Networks are Radial Basis Function Networkscited by 128
  13. 2024Wav-KAN: Wavelet Kolmogorov-Arnold Networkscited by 122
  14. 2020Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networkscited by 87
  15. 2022GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimationcited by 86
  16. 2019Bi-Directional ConvLSTM U-Net with Densley Connected Convolutionscited by 82
  17. 2024fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functionscited by 64
  18. 2024On the expressiveness and spectral bias of KANscited by 37
  19. 2024Exploring the Potential of Polynomial Basis Functions in Kolmogorov-Arnold Networks: A Comparative Study of Different Groups of Polynomialscited by 35
  20. 2023INCODE: Implicit Neural Conditioning with Prior Knowledge Embeddingscited by 31
  21. 2022On the Activation Function Dependence of the Spectral Bias of Neural Networkscited by 28
  22. 2022Fast Neural Kernel Embeddings for General Activationscited by 18
  23. 2021Deep Gaussian Processes: A Surveycited by 13
  24. 2021Learning Continuous Representation of Audio for Arbitrary Scale Super Resolutioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026HOSC: A Periodic Activation with Saturation Control for High-Fidelity Implicit Neural Representationscited by 0