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 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="2409.19472")

Code

Syntology Ran 13 of 22 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 13 ran with no contract checked.

By repository: official repository: 22 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

maorash/local-global-inrs officialmentioned in papermentioned on GitHubpytorchMIT 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; 0 honoured the contract we drafted; 9 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.

13ran
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. “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.

BatchLinear maorash/local-global-inrs/modules.py official repository ran MIT (permissive) · 61a0eddac98610bc · report
LocallyConnectedLayer maorash/local-global-inrs/modules.py official repository ran MIT (permissive) · ddcaba8b880b8459 · report
compute_global_hidden_dim maorash/Local-Global-INRs/compute_partitions.py official repository ran MIT (permissive) · fc4bfe37fd4bad7c · report
compute_hidden_dims maorash/Local-Global-INRs/compute_partitions.py official repository ran MIT (permissive) · be4643ad127966f5 · report
compute_local_hidden_dim maorash/Local-Global-INRs/compute_partitions.py official repository ran MIT (permissive) · efa44d56279c6bdf · report
divergence maorash/Local-Global-INRs/utils.py official repository ran MIT (permissive) · 87e822f4bcfbdac7 · report
function_mse maorash/Local-Global-INRs/loss_functions.py official repository ran MIT (permissive) · 08039d2c26fb8e0f · report
get_mgrid maorash/Local-Global-INRs/dataio.py official repository ran fingerprinted MIT (permissive) · c3c376e19f06a842 · report
get_mgrid maorash/Local-Global-INRs/incode_experiments/dataio.py official repository ran MIT (permissive) · 386eb2e1d4237e59 · report
gradient maorash/Local-Global-INRs/utils.py official repository ran MIT (permissive) · d5a66d1f869bb91d · report
image_mse maorash/Local-Global-INRs/loss_functions.py official repository ran MIT (permissive) · 4c1c1fa3b72b2ac7 · report
laplace maorash/Local-Global-INRs/utils.py official repository ran MIT (permissive) · a2be4be6558869af · report
lin2img maorash/Local-Global-INRs/dataio.py official repository ran MIT (permissive) · 3e90381aa457b40b · report
LocalGlobalBlock maorash/local-global-inrs/modules.py official repository unverified MIT (permissive) · 89328da0bc272173 · report
LocallyConnectedBlock maorash/local-global-inrs/modules.py official repository unverified MIT (permissive) · 4da48b4400a0bc7a · report
first_layer_sine_init maorash/local-global-inrs/modules.py official repository unverified MIT (permissive) · 58eda4091b7584c9 · report
init_weights_elu maorash/local-global-inrs/modules.py official repository unverified MIT (permissive) · 82f21dea7a03c94b · report
init_weights_normal maorash/local-global-inrs/modules.py official repository unverified MIT (permissive) · cb92d23857fe0a7b · report
init_weights_selu maorash/local-global-inrs/modules.py official repository unverified MIT (permissive) · 25a368af1f6243fe · report
init_weights_xavier maorash/local-global-inrs/modules.py official repository unverified MIT (permissive) · c5659f39de5ee097 · report
lin2vid maorash/Local-Global-INRs/dataio.py official repository unverified MIT (permissive) · 1e72ffd7799784e1 · report
sine_init maorash/local-global-inrs/modules.py official repository unverified MIT (permissive) · 34931e02dde165f1 · report

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