pith. sign in

arxiv: 2604.15047 · v1 · submitted 2026-04-16 · 💻 cs.CV

Implicit Neural Representations: A Signal Processing Perspective

Dhananjaya Jayasundara , Vishal M. Patel This is my paper

Pith reviewed 2026-05-10 10:55 UTC · model grok-4.3

classification 💻 cs.CV
keywords implicit neural representationscontinuous signal modelingspectral biasmultiscale representationsneural signal processing3D scene representationsignal compressioninverse problems
0
0 comments X

The pith

Implicit neural representations model signals as continuous functions whose approximation spaces adapt to the data through spectral and multiscale designs.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper traces how implicit neural representations evolved from basic coordinate-based networks that favor low frequencies to more sophisticated designs using periodic activations and structured encodings like hash grids. This evolution allows signals to be modeled continuously, enabling exact differentiation and unified handling of images, audio, video, and 3D geometry. A sympathetic reader would care because this functional view promises more efficient compression, better inverse problem solving in imaging, and scalable representations, while flagging remaining hurdles in stability and large-scale performance.

Core claim

Implicit neural representations parameterize signals as neural networks to create continuous functional representations of images, audio, video, and 3D geometry. Starting from standard networks with a spectral bias toward low frequencies, the field advanced to specialized activations and hierarchical structures that adapt the approximation space to the data's characteristics. This signal-processing lens reveals how INRs support analytical operations through automatic differentiation and finds use in applications such as medical imaging and scene representation, while leaving open questions about theoretical guarantees and interpretability.

What carries the argument

The adaptive approximation space, reshaped through spectral behavior modifications like periodic activations and multiscale structured representations such as hash grid encodings.

Load-bearing premise

That interpreting the development of INRs primarily through the lenses of spectral behavior, sampling theory, and multiscale representation yields the clearest understanding of their capabilities and limitations.

What would settle it

Finding that a non-adaptive, fixed-frequency network achieves comparable or better performance in a high-frequency signal reconstruction task without spectral reshaping would undermine the emphasis on adaptive approximation spaces.

Figures

Figures reproduced from arXiv: 2604.15047 by Dhananjaya Jayasundara, Vishal M. Patel.

Figure 1
Figure 1. Figure 1: A unified view of INRs across signal modalities. The same coordinate-based neural model can represent images, audio, occupancy [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Evolution of INRs. A chronological view of key developments, illustrating the transition from early coordinate-based models to [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Failure of standard activations to preserve signal and operator [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Representation capacity of different INR formulations on [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Hierarchical classification of INR methods based on architectural design and signal support. [PITH_FULL_IMAGE:figures/full_fig_p011_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Illustration of NeRV for video representation. A temporal index [PITH_FULL_IMAGE:figures/full_fig_p016_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: INR decoding of a complex 3D object. The reconstructions [PITH_FULL_IMAGE:figures/full_fig_p017_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Meta-learning for INRs. A meta-learned INR captures shared structure within a signal family, enabling rapid adaptation to new instances with minimal optimization. A natural next step is to move beyond fast adaptation and ask whether the parameters of an INR can be predicted directly, without requiring per-instance iterative optimization at inference time. This is the central idea behind hypernetworks. Inst… view at source ↗
Figure 9
Figure 9. Figure 9: NeRF represents a scene as a continuous function of spatial [PITH_FULL_IMAGE:figures/full_fig_p020_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: INR-based feature representations for classification. Left: [PITH_FULL_IMAGE:figures/full_fig_p021_10.png] view at source ↗
read the original abstract

Implicit neural representations (INRs) mark a fundamental shift in signal modeling, moving from discrete sampled data to continuous functional representations. By parameterizing signals as neural networks, INRs provide a unified framework for representing images, audio, video, 3D geometry, and beyond as continuous functions of their coordinates. This functional viewpoint enables signal operations such as differentiation to be carried out analytically through automatic differentiation rather than through discrete approximations. In this article, we examine the evolution of INRs from a signal processing perspective, emphasizing spectral behavior, sampling theory, and multiscale representation. We trace the progression from standard coordinate based networks, which exhibit a spectral bias toward low frequency components, to more advanced designs that reshape the approximation space through specialized activations, including periodic, localized, and adaptive functions. We also discuss structured representations, such as hierarchical decompositions and hash grid encodings, that improve spatial adaptivity and computational efficiency. We further highlight the utility of INRs across a broad range of applications, including inverse problems in medical and radar imaging, compression, and 3D scene representation. By interpreting INRs as learned signal models whose approximation spaces adapt to the underlying data, this article clarifies the field's core conceptual developments and outlines open challenges in theoretical stability, weight space interpretability, and large scale generalization.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 2 minor

Summary. The manuscript surveys implicit neural representations (INRs) from a signal-processing viewpoint, framing them as continuous functional models of signals that adapt their approximation spaces to data. It traces the development from coordinate-based MLPs exhibiting spectral bias toward low frequencies, through specialized activations (periodic, localized, adaptive) and structured encodings (hierarchical decompositions, hash grids) that enhance spatial adaptivity and efficiency, to applications in inverse problems, compression, and 3D scene representation. The paper interprets INRs as learned signal models and identifies open challenges in theoretical stability, weight-space interpretability, and large-scale generalization.

Significance. If the synthesis is accurate and reasonably comprehensive, the signal-processing lens (spectral behavior, sampling theory, multiscale representation) supplies a coherent organizational framework that could help bridge INR research with classical signal-processing ideas and guide work on the stated challenges. The absence of new derivations or experiments means the significance rests on the clarity and utility of the conceptual mapping rather than on any technical result.

minor comments (2)
  1. Abstract: the final sentence asserts that the article 'clarifies the field's core conceptual developments'; this would be more persuasive if the abstract briefly indicated how the chosen spectral/sampling/multiscale framing differs from or extends prior INR surveys.
  2. The manuscript would be strengthened by an explicit statement, early in the text, of the criteria used to select which INR architectures and applications are covered, to help readers assess completeness.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their concise and accurate summary of the manuscript, for recognizing the value of the signal-processing lens in organizing INR developments, and for the minor-revision recommendation. No specific major comments were raised, so our response below is correspondingly brief.

Circularity Check

0 steps flagged

No circularity: survey framing with no derivations

full rationale

This is a perspective/survey paper that organizes existing INR literature through spectral, sampling, and multiscale lenses. The abstract and structure contain no equations, no fitted parameters, no predictions, and no load-bearing derivations. Claims are clarificatory and organizational rather than deductive; the choice of unifying lens is explicitly presented as interpretive perspective, not as a theorem or result derived from prior self-citations. No steps reduce to self-definition or fitted inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a survey paper; no free parameters, axioms, or invented entities are introduced as part of a new claim.

pith-pipeline@v0.9.0 · 5526 in / 1006 out tokens · 32821 ms · 2026-05-10T10:55:05.606681+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

57 extracted references · 57 canonical work pages

  1. [1]

    The scientist and engineer’s guide to digital signal processing,

    S. W. Smithet al., “The scientist and engineer’s guide to digital signal processing,” 1997

    work page 1997

  2. [2]

    Implicit neural representations with periodic activation functions,

    V . Sitzmann, J. Martel, A. Bergman, D. Lindell, and G. Wet- zstein, “Implicit neural representations with periodic activation functions,”Advances in neural information processing systems, vol. 33, pp. 7462–7473, 2020

    work page 2020

  3. [3]

    On the spectral bias of neural networks,

    N. Rahaman, A. Baratin, D. Arpit, F. Draxler, M. Lin, F. Ham- precht, Y . Bengio, and A. Courville, “On the spectral bias of neural networks,” inInternational conference on machine learning, pp. 5301–5310, PMLR, 2019

    work page 2019

  4. [4]

    Fourier features let networks learn high frequency functions in low dimensional domains,

    M. Tancik, P. Srinivasan, B. Mildenhall, S. Fridovich-Keil, N. Raghavan, U. Singhal, R. Ramamoorthi, J. Barron, and R. Ng, “Fourier features let networks learn high frequency functions in low dimensional domains,”Advances in neural information processing systems, vol. 33, pp. 7537–7547, 2020

    work page 2020

  5. [5]

    Wire: Wavelet implicit neural representations,

    V . Saragadam, D. LeJeune, J. Tan, G. Balakrishnan, A. Veer- araghavan, and R. G. Baraniuk, “Wire: Wavelet implicit neural representations,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 18507–18516, 2023

    work page 2023

  6. [6]

    Beyond periodicity: Towards a unifying framework for activations in coordinate-mlps,

    S. Ramasinghe and S. Lucey, “Beyond periodicity: Towards a unifying framework for activations in coordinate-mlps,” inEu- ropean Conference on Computer Vision, pp. 142–158, Springer, 2022

    work page 2022

  7. [7]

    Miner: Multiscale implicit neural represen- tation,

    V . Saragadam, J. Tan, G. Balakrishnan, R. G. Baraniuk, and A. Veeraraghavan, “Miner: Multiscale implicit neural represen- tation,” inEuropean Conference on Computer Vision, pp. 318– 333, Springer, 2022

    work page 2022

  8. [8]

    Finer: Flexible spectral-bias tuning in implicit neural representation by variable-periodic activation functions,

    Z. Liu, H. Zhu, Q. Zhang, J. Fu, W. Deng, Z. Ma, Y . Guo, and X. Cao, “Finer: Flexible spectral-bias tuning in implicit neural representation by variable-periodic activation functions,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2713–2722, 2024

    work page 2024

  9. [9]

    Sinr: Sparsity driven compressed implicit neural representations,

    D. Jayasundara, S. Rajagopalan, Y . Ranasinghe, T. D. Tran, and V . M. Patel, “Sinr: Sparsity driven compressed implicit neural representations,” inProceedings of the Computer Vision and Pattern Recognition Conference, pp. 3061–3070, 2025

    work page 2025

  10. [10]

    Regularize implicit neural repre- sentation by itself,

    Z. Li, H. Wang, and D. Meng, “Regularize implicit neural repre- sentation by itself,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10280–10288, 2023

    work page 2023

  11. [11]

    Signal processing for implicit neural representations,

    D. Xu, P. Wang, Y . Jiang, Z. Fan, and Z. Wang, “Signal processing for implicit neural representations,”Advances in Neural Information Processing Systems, vol. 35, pp. 13404– 13418, 2022

    work page 2022

  12. [12]

    Pin: Prolate spheroidal wave function-based implicit neural rep- resentations,

    D. Jayasundara, H. Zhao, D. Labate, and V . M. Patel, “Pin: Prolate spheroidal wave function-based implicit neural rep- resentations,” inThe Thirteenth International Conference on Learning Representations, 2025

    work page 2025

  13. [13]

    Stereoinr: Cross-view geometry consistent stereo super resolution with implicit neural representation,

    Y . Liu, X. Liu, Y . Wan, P. Xia, Q. Wu, and Y . Zhang, “Stereoinr: Cross-view geometry consistent stereo super resolution with implicit neural representation,” inProceedings of the 33rd ACM International Conference on Multimedia, pp. 1003–1012, 2025

    work page 2025

  14. [14]

    Nerv: Neural representations for videos,

    H. Chen, B. He, H. Wang, Y . Ren, S. N. Lim, and A. Shri- vastava, “Nerv: Neural representations for videos,”Advances in Neural Information Processing Systems, vol. 34, pp. 21557– 21568, 2021

    work page 2021

  15. [15]

    Nerf: Representing scenes as neural radiance fields for view synthesis,

    B. Mildenhall, P. P. Srinivasan, M. Tancik, J. T. Barron, R. Ramamoorthi, and R. Ng, “Nerf: Representing scenes as neural radiance fields for view synthesis,”Communications of the ACM, vol. 65, no. 1, pp. 99–106, 2021

    work page 2021

  16. [16]

    Instant neural graphics primitives with a multiresolution hash encoding,

    T. M ¨uller, A. Evans, C. Schied, and A. Keller, “Instant neural graphics primitives with a multiresolution hash encoding,”ACM transactions on graphics (TOG), vol. 41, no. 4, pp. 1–15, 2022

    work page 2022

  17. [17]

    Improved implicit neural repre- sentation with fourier reparameterized training,

    K. Shi, X. Zhou, and S. Gu, “Improved implicit neural repre- sentation with fourier reparameterized training,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 25985–25994, 2024

    work page 2024

  18. [18]

    Mire: Matched implicit neural representations,

    D. Jayasundara, H. Zhao, D. Labate, and V . M. Patel, “Mire: Matched implicit neural representations,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8279–8288, 2025

    work page 2025

  19. [19]

    A sampling theory perspective on activations for im- plicit neural representations,

    H. Saratchandran, S. Ramasinghe, V . Shevchenko, A. Long, and S. Lucey, “A sampling theory perspective on activations for im- plicit neural representations,”arXiv preprint arXiv:2402.05427, 2024

    work page arXiv 2024

  20. [20]

    Cosmo-inr: Complex sinusoidal modulation for implicit neural represen- tations,

    P. Thennakoon, A. Ranasinghe, M. De Silva, B. Epakanda, R. Godaliyadda, P. Ekanayake, and V . Herath, “Cosmo-inr: Complex sinusoidal modulation for implicit neural represen- tations,”arXiv preprint arXiv:2505.11640, 2025

    work page arXiv 2025

  21. [21]

    Sl2a-inr: Single-layer learnable activation for implicit neural representation,

    R. Rezaeian, M. Heidari, R. Azad, D. Merhof, H. Soltanian- Zadeh, and I. Hacihaliloglu, “Sl2a-inr: Single-layer learnable activation for implicit neural representation,” inProceedings of the IEEE/CVF International Conference on Computer Vision, pp. 26065–26074, 2025

    work page 2025

  22. [22]

    Multiplicative filter networks,

    R. Fathony, A. K. Sahu, D. Willmott, and J. Z. Kolter, “Multiplicative filter networks,” inInternational conference on learning representations, 2020

    work page 2020

  23. [23]

    Incode: Implicit neural conditioning with prior knowledge em- beddings,

    A. Kazerouni, R. Azad, A. Hosseini, D. Merhof, and U. Bagci, “Incode: Implicit neural conditioning with prior knowledge em- beddings,” inProceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1298–1307, 2024

    work page 2024

  24. [24]

    Hosc: A periodic activation function for preserving sharp features in implicit neural representations,

    D. Serrano, J. Szymkowiak, and P. Musialski, “Hosc: A periodic activation function for preserving sharp features in implicit neural representations,”arXiv preprint arXiv:2401.10967, 2024

    work page arXiv 2024

  25. [25]

    Fresh: Frequency shifting for accelerated neural representation learning,

    A. Kania, M. Mihajlovic, S. Prokudin, J. Tabor, P. Spurek,et al., “Fresh: Frequency shifting for accelerated neural representation learning,”arXiv preprint arXiv:2410.05050, 2024

    work page arXiv 2024

  26. [26]

    A structured dictionary perspective on implicit neural repre- sentations,

    G. Y ¨uce, G. Ortiz-Jim ´enez, B. Besbinar, and P. Frossard, “A structured dictionary perspective on implicit neural repre- sentations,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 19228–19238, 2022

    work page 2022

  27. [27]

    Acorn: Adaptive coordinate networks for neural scene representation

    J. N. Martel, D. B. Lindell, C. Z. Lin, E. R. Chan, M. Monteiro, and G. Wetzstein, “Acorn: Adaptive coordinate networks for neural scene representation,”arXiv preprint arXiv:2105.02788, 2021

    work page arXiv 2021

  28. [28]

    Hy- persound: Generating implicit neural representations of audio signals with hypernetworks,

    F. Szatkowski, K. J. Piczak, P. Spurek, J. Tabor,et al., “Hy- persound: Generating implicit neural representations of audio signals with hypernetworks,”arXiv preprint arXiv:2211.01839, 2022

    work page arXiv 2022

  29. [29]

    Siamese siren: Audio compression with implicit neural representations.arXiv preprint arXiv:2306.12957, 2023

    L. A. Lanzend ¨orfer and R. Wattenhofer, “Siamese siren: Au- dio compression with implicit neural representations,”arXiv preprint arXiv:2306.12957, 2023

    work page arXiv 2023

  30. [30]

    Hnerv: A hybrid neural representation for videos,

    H. Chen, M. Gwilliam, S.-N. Lim, and A. Shrivastava, “Hnerv: A hybrid neural representation for videos,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10270–10279, 2023

    work page 2023

  31. [31]

    Hinerv: Video compression with hierarchical encoding-based neural representation,

    H. M. Kwan, G. Gao, F. Zhang, A. Gower, and D. Bull, “Hinerv: Video compression with hierarchical encoding-based neural representation,”Advances in Neural Information Processing Systems, vol. 36, pp. 72692–72704, 2023. 24

    work page 2023

  32. [32]

    Implicit neural rep- resentation learning for hyperspectral image super-resolution,

    K. Zhang, D. Zhu, X. Min, and G. Zhai, “Implicit neural rep- resentation learning for hyperspectral image super-resolution,” IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–12, 2022

    work page 2022

  33. [33]

    Spectral-wise implicit neural representation for hyperspectral image reconstruction,

    H. Chen, W. Zhao, T. Xu, G. Shi, S. Zhou, P. Liu, and J. Li, “Spectral-wise implicit neural representation for hyperspectral image reconstruction,”IEEE Transactions on Circuits and Sys- tems for Video Technology, vol. 34, no. 5, pp. 3714–3727, 2023

    work page 2023

  34. [34]

    Neural vector fields for implicit surface representation and inference,

    E. Mello Rella, A. Chhatkuli, E. Konukoglu, and L. Van Gool, “Neural vector fields for implicit surface representation and inference,”International Journal of Computer Vision, vol. 133, no. 4, pp. 1855–1878, 2025

    work page 2025

  35. [35]

    Metasdf: Meta-learning signed distance functions,

    V . Sitzmann, E. Chan, R. Tucker, N. Snavely, and G. Wetzstein, “Metasdf: Meta-learning signed distance functions,”Advances in Neural Information Processing Systems, vol. 33, pp. 10136– 10147, 2020

    work page 2020

  36. [36]

    Implicit neural representations for image compression,

    Y . Str ¨umpler, J. Postels, R. Yang, L. V . Gool, and F. Tombari, “Implicit neural representations for image compression,” in European conference on computer vision, pp. 74–91, Springer, 2022

    work page 2022

  37. [37]

    Inriq: Im- plicit neural representation for image quality assessment,

    D. Jayasundara, S. Rajagopalan, and V . M. Patel, “Inriq: Im- plicit neural representation for image quality assessment,”

    work page

  38. [38]

    COIN++: Neural compression across modalities,

    E. Dupont, H. Loya, M. Alizadeh, A. Goli ´nski, Y . W. Teh, and A. Doucet, “Coin++: Neural compression across modalities,” arXiv preprint arXiv:2201.12904, 2022

    work page arXiv 2022

  39. [39]

    Hyper-network based implicit neural representa- tions for image reconstruction and classification,

    E. Grigokhan, “Hyper-network based implicit neural representa- tions for image reconstruction and classification,” 2021. Course Project Report

    work page 2021

  40. [40]

    Hyperinr: A fast and predictive hypernetwork for implicit neural representations via knowledge distillation,

    Q. Wu, D. Bauer, Y . Chen, and K.-L. Ma, “Hyperinr: A fast and predictive hypernetwork for implicit neural representations via knowledge distillation,”arXiv preprint arXiv:2304.04188, 2023

    work page arXiv 2023

  41. [41]

    Implicit neural representation in medical imaging: A comparative survey,

    A. Molaei, A. Aminimehr, A. Tavakoli, A. Kazerouni, B. Azad, R. Azad, and D. Merhof, “Implicit neural representation in medical imaging: A comparative survey,” inProceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2381–2391, 2023

    work page 2023

  42. [42]

    Nesvor: implicit neural representation for slice-to-volume reconstruction in mri,

    J. Xu, D. Moyer, B. Gagoski, J. E. Iglesias, P. E. Grant, P. Golland, and E. Adalsteinsson, “Nesvor: implicit neural representation for slice-to-volume reconstruction in mri,”IEEE transactions on medical imaging, vol. 42, no. 6, pp. 1707–1719, 2023

    work page 2023

  43. [43]

    Implicit neural representations for medical imaging segmentation,

    M. O. Khan and Y . Fang, “Implicit neural representations for medical imaging segmentation,” inInternational conference on medical image computing and computer-assisted intervention, pp. 433–443, Springer, 2022

    work page 2022

  44. [44]

    Fit pixels, get labels: Meta-learned implicit networks for image segmenta- tion,

    K. Vyas, A. Veeraraghavan, and G. Balakrishnan, “Fit pixels, get labels: Meta-learned implicit networks for image segmenta- tion,” inInternational Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 194–203, Springer, 2025

    work page 2025

  45. [45]

    Neural implicit representa- tions for 3d synthetic aperture radar imaging,

    N. Sugavanam and E. Ertin, “Neural implicit representa- tions for 3d synthetic aperture radar imaging,”arXiv preprint arXiv:2602.17556, 2026

    work page arXiv 2026

  46. [46]

    Implicit neural rep- resentation with imaging geometry for sar target recognition,

    Z. Cheng, Y . Ding, C. Qu, and B. Chen, “Implicit neural rep- resentation with imaging geometry for sar target recognition,” IEEE Transactions on Aerospace and Electronic Systems, 2025

    work page 2025

  47. [47]

    Spinrv2: Implicit neural rep- resentation for passband fmcw radars,

    H. Takawale and N. Roy, “Spinrv2: Implicit neural rep- resentation for passband fmcw radars,”arXiv preprint arXiv:2506.08163, 2025

    work page arXiv 2025

  48. [48]

    Coin: Compression with implicit neural representations,

    E. Dupont, A. Goli ´nski, M. Alizadeh, Y . W. Teh, and A. Doucet, “Coin: Compression with implicit neural representations,”arXiv preprint arXiv:2103.03123, 2021

    work page arXiv 2021

  49. [49]

    Differentiable rendering: A survey.arXiv preprint arXiv:2006.12057, 2020

    H. Kato, D. Beker, M. Morariu, T. Ando, T. Matsuoka, W. Kehl, and A. Gaidon, “Differentiable rendering: A survey,”arXiv preprint arXiv:2006.12057, 2020

    work page arXiv 2006

  50. [50]

    Spin- nerf: Multiview segmentation and perceptual inpainting with neural radiance fields,

    A. Mirzaei, T. Aumentado-Armstrong, K. G. Derpanis, J. Kelly, M. A. Brubaker, I. Gilitschenski, and A. Levinshtein, “Spin- nerf: Multiview segmentation and perceptual inpainting with neural radiance fields,” inProceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition, pp. 20669– 20679, 2023

    work page 2023

  51. [51]

    Implicit neural representation as vectorizer for classification task applied to diverse data structures,

    T. Malherbe, “Implicit neural representation as vectorizer for classification task applied to diverse data structures,” inFirst ContinualAI Unconference-Preregistration Track Second Stage, 2024

    work page 2024

  52. [52]

    Resolution- agnostic remote sensing scene classification with implicit neural representations,

    K. Chen, W. Li, J. Chen, Z. Zou, and Z. Shi, “Resolution- agnostic remote sensing scene classification with implicit neural representations,”IEEE Geoscience and Remote Sensing Letters, vol. 20, pp. 1–5, 2022

    work page 2022

  53. [53]

    Infer: Implicit neural features for exposing realism,

    D. Jayasundara, K. Narayan, and V . M. Patel, “Infer: Implicit neural features for exposing realism,”

    work page

  54. [54]

    Learning transferable visual models from natural language supervision,

    A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark,et al., “Learning transferable visual models from natural language supervision,” inInternational conference on machine learning, pp. 8748–8763, PmLR, 2021

    work page 2021

  55. [55]

    End-to-end implicit neural rep- resentations for classification,

    A. Gielisse and J. van Gemert, “End-to-end implicit neural rep- resentations for classification,” inProceedings of the Computer Vision and Pattern Recognition Conference, pp. 18728–18737, 2025

    work page 2025

  56. [56]

    Perceptual image quality assessment: a survey,

    G. Zhai and X. Min, “Perceptual image quality assessment: a survey,”Science China Information Sciences, vol. 63, no. 11, p. 211301, 2020

    work page 2020

  57. [57]

    Beyond pixels: Medical image quality assessment with implicit neural representations,

    C. ¨Ozer, P. Rygiel, B. de Wilde, I. ¨Oks¨uz, and J. M. Wolterink, “Beyond pixels: Medical image quality assessment with implicit neural representations,” inInternational Workshop on Machine Learning in Medical Imaging, pp. 359–368, Springer, 2025

    work page 2025