Papers › Towards Croppable Implicit Neural Representations

Towards Croppable Implicit Neural Representations

28 Sep 2024arXiv:2409.19472archive 2025-07-28

Maor Ashkenazi, Eran Treister

Implicit Neural Representations (INRs) have peaked interest in recent years due to their ability to encode natural signals using neural networks. While INRs allow for useful applications such as interpolating new coordinates and signal compression, their black-box nature makes it difficult to modify them post-training. In this paper we explore the idea of editable INRs, and specifically focus on the widely used cropping operation. To this end, we present Local-Global SIRENs -- a novel INR architecture that supports cropping by design. Local-Global SIRENs are based on combining local and global feature extraction for signal encoding. What makes their design unique is the ability to effortlessly remove specific portions of an encoded signal, with a proportional weight decrease. This is achieved by eliminating the corresponding weights from the network, without the need for retraining. We further show how this architecture can be used to support the straightforward extension of previously encoded signals. Beyond signal editing, we examine how the Local-Global approach can accelerate training, enhance encoding of various signals, improve downstream performance, and be applied to modern INRs such as INCODE, highlighting its potential and flexibility. Code is available at https://github.com/maorash/Local-Global-INRs.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

Syntology holds a reference implementation of Local-Global SIRENs, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Local-Global SIRENs') (how to connect); the free check have('2409.19472') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 22 code samples harvested from 1 repository linked to this paper: 13 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 1 repository, 13 ran (11 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

maorash/local-global-inrs officialmentioned in papermentioned on GitHubpytorchMITSyntology: 22 samples, 13 ran (2 instrument-failed) · 9 unverified 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

22 samples harvested: 13 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong
10ran
9unverified

Licence: 0 of the 22 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 maorash/local-global-inrs. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

maorash/local-global-inrs official repository 22 samples, 13 ran (2 instrument-failed) · 9 unverified
BatchLinear modules.py ran MIT (permissive) · 61a0eddac98610bc · report fixture: signature input:Tensor/3/float · returned Tensor · level recorded 2026-09-24
LocallyConnectedLayer modules.py ran MIT (permissive) · ddcaba8b880b8459 · report fixture: returned LocallyConnectedLayer · level recorded 2026-09-22
compute_global_hidden_dim compute_partitions.py ran MIT (permissive) · fc4bfe37fd4bad7c · report fixture: signature total_param_number:int/0/int, global_weights_factor:float/0/float, in_dim:int/0/int, hidden_layers:int/0/int · returned tuple · level recorded 2026-09-24
compute_hidden_dims compute_partitions.py ran MIT (permissive) · be4643ad127966f5 · report fixture: signature total_param_number:int/0/int, global_weights_factor:float/0/float, in_dim:int/0/int, output_dim:int/0/int, hidden_layers:int/0/int, groups:int/0/int · returned tuple · level recorded 2026-09-24
compute_local_hidden_dim compute_partitions.py ran MIT (permissive) · efa44d56279c6bdf · report fixture: signature in_dim:int/0/int, output_dim:int/0/int, hidden_layers:int/0/int, groups:int/0/int, target_param_number:int/0/int · returned tuple · level recorded 2026-09-24
divergence in 15 papers utils.py ran MIT (permissive) · 87e822f4bcfbdac7 · report fixture: signature y:Tensor/2/float, x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
function_mse loss_functions.py ran MIT (permissive) · 08039d2c26fb8e0f · report fixture: signature model_output:dict/0/?, gt:dict/0/? · returned dict · level recorded 2026-09-24
get_mgrid in 16 papers dataio.py ran · honoured contract fingerprinted MIT (permissive) · c3c376e19f06a842 · report fixture: signature sidelen:int/0/int, dim:int/0/int · returned Tensor · level recorded 2026-09-24
get_mgrid in 16 papers incode_experiments/dataio.py ran MIT (permissive) · 386eb2e1d4237e59 · report fixture: signature sidelen:int/0/int, dim:int/0/int, zero_to_one:bool/0/bool · returned Tensor · level recorded 2026-09-24
gradient in 21 papers utils.py ran · our draft was wrong MIT (permissive) · d5a66d1f869bb91d · report fixture: signature y:Tensor/0/float, x:Tensor/2/float, grad_outputs:Tensor/0/float · returned Tensor · level recorded 2026-09-24
image_mse in 6 papers loss_functions.py ran MIT (permissive) · 4c1c1fa3b72b2ac7 · report fixture: signature mask:NoneType/0/?, model_output:dict/0/?, gt:dict/0/? · returned dict · level recorded 2026-09-24
laplace in 12 papers utils.py ran · our draft was wrong MIT (permissive) · a2be4be6558869af · report fixture: signature y:Tensor/2/float, x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
lin2img in 5 papers dataio.py ran MIT (permissive) · 3e90381aa457b40b · report fixture: signature tensor:Tensor/3/float, image_resolution:NoneType/0/?, slices:NoneType/0/? · returned Tensor · level recorded 2026-09-24
LocalGlobalBlock modules.py unverified MIT (permissive) · 89328da0bc272173 · report
LocallyConnectedBlock modules.py unverified MIT (permissive) · 4da48b4400a0bc7a · report
first_layer_sine_init modules.py unverified MIT (permissive) · 58eda4091b7584c9 · report
init_weights_elu modules.py unverified MIT (permissive) · 82f21dea7a03c94b · report
init_weights_normal in 5 papers modules.py unverified MIT (permissive) · cb92d23857fe0a7b · report
init_weights_selu modules.py unverified MIT (permissive) · 25a368af1f6243fe · report
init_weights_xavier in 5 papers modules.py unverified MIT (permissive) · c5659f39de5ee097 · report
lin2vid dataio.py unverified MIT (permissive) · 1e72ffd7799784e1 · report
sine_init modules.py unverified MIT (permissive) · 34931e02dde165f1 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for Local-Global SIRENs (graph method: Local-Global SIRENs), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. compute_num_groups entry · level 2 · ran · ff40bcd2911b1b87a30b0f0d9ce44a7994e44a7942479e5b111536f6d8e570a7

harvested Assembly for Local-Global SIRENs (graph method: Local-Global SIRENs). 11 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. LocalGlobalBlock entry · level 0 · unverified · 89328da0bc272173
  2. BatchLinear model · level 1 · ran · 61a0eddac98610bc
  3. LocallyConnectedBlock model · level 0 · unverified · 4da48b4400a0bc7a
  4. LocallyConnectedLayer helper · level 1 · ran · ddcaba8b880b8459
  5. Sine model · level 1 · ran · 7bbf8646a3306d9e
  6. first_layer_sine_init helper · level 0 · unverified · 58eda4091b7584c9
  7. init_weights_elu helper · level 0 · unverified · 82f21dea7a03c94b
  8. init_weights_normal helper · level 0 · unverified · cb92d23857fe0a7b
  9. init_weights_selu helper · level 0 · unverified · 25a368af1f6243fe
  10. init_weights_xavier helper · level 0 · unverified · c5659f39de5ee097
  11. sine_init helper · level 0 · unverified · 34931e02dde165f1

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2409.19472") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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