Papers › Implicit Neural Representations with Periodic Activation Functions

Implicit Neural Representations with Periodic Activation Functions

17 Jun 2020NeurIPS 2020 12arXiv:2006.09661archive 2025-07-28

Vincent Sitzmann, Julien N. P. Martel, Alexander W. Bergman, David B. Lindell, Gordon Wetzstein

Implicitly defined, continuous, differentiable signal representations parameterized by neural networks have emerged as a powerful paradigm, offering many possible benefits over conventional representations. However, current network architectures for such implicit neural representations are incapable of modeling signals with fine detail, and fail to represent a signal's spatial and temporal derivatives, despite the fact that these are essential to many physical signals defined implicitly as the solution to partial differential equations. We propose to leverage periodic activation functions for implicit neural representations and demonstrate that these networks, dubbed sinusoidal representation networks or Sirens, are ideally suited for representing complex natural signals and their derivatives. We analyze Siren activation statistics to propose a principled initialization scheme and demonstrate the representation of images, wavefields, video, sound, and their derivatives. Further, we show how Sirens can be leveraged to solve challenging boundary value problems, such as particular Eikonal equations (yielding signed distance functions), the Poisson equation, and the Helmholtz and wave equations. Lastly, we combine Sirens with hypernetworks to learn priors over the space of Siren functions.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2006.09661")

Code

Syntology Ran 49 of 71 code samples harvested from 18 repositories linked to this paper; 22 have no recorded run. Of those that ran: 2 ran · honoured contract; 5 ran · our draft was wrong; 42 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 7 ran; community (archive-listed): 57 samples from 17 repositories, 42 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

25 repositories listed; official and paper-mentioned ones first.

vsitzmann/siren officialmentioned on GitHubpytorchMIT report
Daniel-H-99/SIREN mentioned on GitHubpytorch report
TheStageAI/TorchIntegral mentioned on GitHubpytorch report
WANG-KX/SIREN-2D mentioned on GitHubpytorch report
andreasjansson/fmsynth mentioned on GitHubpytorch report
arihaz/ImplicitNeuralRepresentations mentioned on GitHubpytorch report
dalmia/siren mentioned on GitHubpytorch report
ecovision-uzh/climplicit mentioned on GitHubpytorch report
eitan3/siren_gluon mentioned on GitHubmxnet report
linusnie/diffcd mentioned on GitHubjax report
locuslab/impsq mentioned on GitHubpytorch report
lucidrains/siren-pytorch mentioned on GitHubpytorch report
marccoru/locationencoder mentioned on GitHubpytorch report
mjhwright/error-correction mentioned on GitHubpytorch report
palombom/sirenmri mentioned on GitHubpytorch report
scart97/Siren-fastai2 mentioned on GitHubpytorch report
titu1994/tf_SIREN mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

71 samples harvested; 49 ran; 2 honoured the contract we drafted; 22 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
5ran · our draft was wrong
42ran
22unverified

Licence: 8 of the 71 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 18 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

channel_last vsitzmann/siren/modules.py official repository ran fingerprinted MIT (permissive) · ca25202da0ba3ba4 · report
compl_conj vsitzmann/siren/modules.py official repository ran fingerprinted MIT (permissive) · 50122beab0f810e1 · report
divergence vsitzmann/siren/diff_operators.py official repository ran MIT (permissive) · 87e822f4bcfbdac7 · report
get_mgrid vsitzmann/siren/dataio.py official repository ran fingerprinted MIT (permissive) · c3c376e19f06a842 · report
hessian vsitzmann/siren/diff_operators.py official repository ran MIT (permissive) · fd089b9f4b8749ab · report
laplace vsitzmann/siren/diff_operators.py official repository ran MIT (permissive) · a2be4be6558869af · report
lin2img vsitzmann/siren/dataio.py official repository ran MIT (permissive) · 9d902c538061fea5 · report
animated_line_plot vsitzmann/siren/make_figures.py official repository unverified MIT (permissive) · b8053a02b885c59e · report
conv3x3 vsitzmann/siren/modules.py official repository unverified MIT (permissive) · 46ad0f97079d1fd8 · report
densely_sample_activations vsitzmann/siren/utils.py official repository unverified MIT (permissive) · d0cf6c9ce260f1a4 · report
extract_from_summary vsitzmann/siren/make_figures.py official repository unverified MIT (permissive) · 71b652cef0836b80 · report
grads2img vsitzmann/siren/dataio.py official repository unverified MIT (permissive) · 2d7e4df5345f8188 · report
image_l1 vsitzmann/siren/loss_functions.py official repository unverified MIT (permissive) · 81fe748ce57e9fae · report
image_mse vsitzmann/siren/loss_functions.py official repository unverified MIT (permissive) · 196981f676d3a9d8 · report
BatchLinear TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) ran MIT (permissive) · 976f5acdf961701c · report
FCBlock TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 8ede319230f3b9c5 · report
ImageDownsampling TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) ran MIT (permissive) · 1ad216217b5c6292 · report
PosEncodingNeRF TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 96a71871fc866141 · report
RBFLayer TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 74c875b042d85c09 · report
SIREN dalmia/siren/siren/siren.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · d974796661d1e3ea · report
SIREN Daniel-H-99/SIREN/models.py community (archive-listed) ran fingerprinted no licence file found · pointer only · 25b93817248bf804 · report
SIREN locuslab/impsq/modules/models.py community (archive-listed) ran fingerprinted no licence file found · pointer only · 9dbc91c61f8d9f89 · report
SIRENInitializer titu1994/tf_SIREN/tf_siren/siren.py community (archive-listed) ran MIT (permissive) · b3b681c70d532217 · report
SIRENInitializer zion-king/Tensorflow-Sinusodial-Representation-Networks-SIREN/tf_siren/siren.py community (archive-listed) ran MIT (permissive) · 7850486bfddc6c83 · report
Sine marccoru/locationencoder/locationencoder/nn/siren.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 9ea2ac2f593eb96a · report
Sine TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 7bbf8646a3306d9e · report
Sine titu1994/tf_SIREN/tf_siren/siren.py community (archive-listed) ran MIT (permissive) · 1d752eb8bb968496 · report
Sine mjhwright/error-correction/network.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · dc2056da4db84fc9 · report
Sine palombom/sirenmri/siren.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 377aa085c43d01c6 · report
Sine dalmia/siren/siren/siren.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 5dfb17433aff0114 · report
Sine ecovision-uzh/climplicit/quickstart/siren.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 2389bbb56014ff60 · report
Sine zion-king/Tensorflow-Sinusodial-Representation-Networks-SIREN/tf_siren/siren.py community (archive-listed) ran MIT (permissive) · 7c31228c86957fbf · report
SineLayer jankrepl/mildlyoverfitted/github_adventures/siren/core.py community (archive-listed) ran MIT (permissive) · 2043cfd7f293fb9e · report
SineLayer arihaz/ImplicitNeuralRepresentations/network.py community (archive-listed) ran no licence file found · pointer only · 7877368eae84c292 · report
SineLayer MaximeVandegar/Papers-in-100-Lines-of-Code/Implicit_Neural_Representations_with_Periodic_Activation_Functions/siren.py community (archive-listed) ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 4b770f57b782b848 · report
SingleBVPNet TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 92f860754ce944d1 · report
SinusodialRepresentationDense titu1994/tf_SIREN/tf_siren/siren.py community (archive-listed) ran MIT (permissive) · e7f217d13dd1e5d9 · report
SinusodialRepresentationDense zion-king/Tensorflow-Sinusodial-Representation-Networks-SIREN/tf_siren/siren.py community (archive-listed) ran MIT (permissive) · 184b236f39ccaca1 · report
Siren marccoru/locationencoder/locationencoder/nn/siren.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 2aa2597d8bd3bb93 · report
Siren lucidrains/siren-pytorch/siren_pytorch/siren_pytorch.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 5b35db3519256685 · report
Siren mjhwright/error-correction/network.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 08022569ff28ebd6 · report
Siren palombom/sirenmri/siren.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 4030b7a0e9748b71 · report
Siren ecovision-uzh/climplicit/quickstart/siren.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 7b1fb4633b5400fd · report
Siren arihaz/ImplicitNeuralRepresentations/network.py community (archive-listed) ran no licence file found · pointer only · 5a2ba67aad35b0e7 · report
Siren scart97/Siren-fastai2/siren.py community (archive-listed) ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 5961b5f54fb8d3f8 · report
Siren MaximeVandegar/Papers-in-100-Lines-of-Code/Implicit_Neural_Representations_with_Periodic_Activation_Functions/siren.py community (archive-listed) ran · metamorphic tier: invariant MIT (permissive) · 5569fd5a29189c82 · report
SirenLayer palombom/sirenmri/siren.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 8ac1c1befb2f7857 · report
SirenNet marccoru/locationencoder/locationencoder/nn/siren.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · da5b5f2242dabaf8 · report
SirenNet ecovision-uzh/climplicit/quickstart/siren.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 116c403f9b64d6f9 · report
cast_tuple marccoru/locationencoder/locationencoder/nn/siren.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · 7bd1641f670e602d · report
get_subdict TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) ran · our draft was wrong MIT (permissive) · cc9c74f5df741aef · report
non_zero_mean linusnie/diffcd/diffcd/networks.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · a543cc7ec13c4381 · report
safe_softplus linusnie/diffcd/diffcd/networks.py community (archive-listed) ran · honoured contract fingerprinted Apache-2.0 (permissive) · 74a2fc2b7bb9535e · report
siren_uniform_ dalmia/siren/siren/siren.py community (archive-listed) ran · our draft was wrong MIT (permissive) · a87fd526d4a3314f · report
softplus linusnie/diffcd/diffcd/networks.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 412ae5f90dd4d2df · report
zero_mean linusnie/diffcd/diffcd/networks.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · bd03e58827e3f72d · report
ActivationFunction linusnie/diffcd/diffcd/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · c156c41aef66579a · report
GridSampleWeightsBase TheStageAI/TorchIntegral/torch_integral/parametrizations/interpolation_weights.py community (archive-listed) unverified Apache-2.0 (permissive) · b273c9f1b2897ba2 · report
IWeights TheStageAI/TorchIntegral/torch_integral/parametrizations/interpolation_weights.py community (archive-listed) unverified Apache-2.0 (permissive) · 7d35faf2895d98fb · report
MLP linusnie/diffcd/diffcd/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · d09b082f03330456 · report
MetaModule TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) unverified MIT (permissive) · 78371e32f4b5df03 · report
MetaSequential TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) unverified MIT (permissive) · fa9f394eb26ff78f · report
first_layer_sine_init TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) unverified MIT (permissive) · 2960e2b2441e1027 · report
get_activation_function linusnie/diffcd/diffcd/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · c1c479c977b6d4f1 · report
init_weights mjhwright/error-correction/network.py community (archive-listed) unverified MIT (permissive) · f8f7249b7c7945f9 · report
init_weights_elu TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) unverified MIT (permissive) · d6d40d78467a0c0f · report
init_weights_normal TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) unverified MIT (permissive) · ff3d2903768a5844 · report
init_weights_selu TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) unverified MIT (permissive) · 3960ccb751ee19a9 · report
init_weights_xavier TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) unverified MIT (permissive) · a0ced3e7f2e93303 · report
paper_init_ jankrepl/mildlyoverfitted/github_adventures/siren/core.py community (archive-listed) unverified MIT (permissive) · 915e2db004fc66a4 · report
sine_init TalFurman/Implict_neural_representation_of_images/modules.py community (archive-listed) unverified MIT (permissive) · 0bef15aad24e7f4a · report

Tasks

Image Inpainting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Siren

Siren

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections