Papers › SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction

SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction

17 Sep 2024arXiv:2409.11211archive 2025-07-28

Marko Mihajlovic, Sergey Prokudin, Siyu Tang, Robert Maier, Federica Bogo, Tony Tung, Edmond Boyer

Digitizing 3D static scenes and 4D dynamic events from multi-view images has long been a challenge in computer vision and graphics. Recently, 3D Gaussian Splatting (3DGS) has emerged as a practical and scalable reconstruction method, gaining popularity due to its impressive reconstruction quality, real-time rendering capabilities, and compatibility with widely used visualization tools. However, the method requires a substantial number of input views to achieve high-quality scene reconstruction, introducing a significant practical bottleneck. This challenge is especially severe in capturing dynamic scenes, where deploying an extensive camera array can be prohibitively costly. In this work, we identify the lack of spatial autocorrelation of splat features as one of the factors contributing to the suboptimal performance of the 3DGS technique in sparse reconstruction settings. To address the issue, we propose an optimization strategy that effectively regularizes splat features by modeling them as the outputs of a corresponding implicit neural field. This results in a consistent enhancement of reconstruction quality across various scenarios. Our approach effectively handles static and dynamic cases, as demonstrated by extensive testing across different setups and scene complexities.

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.

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

Code

Syntology 19 code samples: 18 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 19: 12 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 5 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 18 samples from 1 repository, 11 ran (8 with no instrument failure; 3 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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.

markomih/splatfields mentioned on GitHubpytorchSyntology: 18 samples, 11 ran (3 instrument-failed) · 7 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

19 samples harvested: 12 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 5 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · honoured contract
2ran · our draft was wrong
1ran; the contract check could not run
4ran
7unverified

Licence: 19 of the 19 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 markomih/splatfields. 1 sample is listed last, in a group without a repository. “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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

markomih/splatfields community (archive-listed) 18 samples, 11 ran (3 instrument-failed) · 7 unverified
Embedder in 18 papers scene/deform_model.py ran no licence file found · pointer only · e61cc7bddc7d86e5 · report fixture: returned Embedder · level recorded 2026-09-22
Linear in 127 papers scene/deform_model.py ran · metamorphic tier: deterministic no licence file found · pointer only · ff83d06e72a107a2 · report fixture: returned Linear · level recorded 2026-09-22
Sine in 13 papers scene/deform_model.py ran fingerprinted no licence file found · pointer only · 08438c622b9a2549 · report fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-24
SirenMLP scene/deform_model.py ran · metamorphic tier: deterministic no licence file found · pointer only · a10256972809fc78 · report fixture: returned SirenMLP · level recorded 2026-09-22
exp_so3 in 5 papers scene/deform_model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 8bec3035faa583da · report fixture: signature w:Tensor/2/float, theta:Tensor/1/float · returned Tensor · level recorded 2026-09-22
from_homogenous scene/deform_model.py ran · honoured contract fingerprinted no licence file found · pointer only · 5097b2d841c17f14 · report fixture: signature v:Tensor/2/float · returned Tensor · level recorded 2026-09-22
get_embedder in 88 papers scene/deform_model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 8d68829e9ebe344d · report fixture: signature multires:int/0/int, i:int/0/int · returned tuple · level recorded 2026-09-22
get_expon_lr_func in 14 papers scene/deform_model.py ran · our draft was wrong no licence file found · pointer only · 7325f65ee1e29543 · report fixture: signature lr_init:float/0/float, lr_final:float/0/float, lr_delay_steps:int/0/int, lr_delay_mult:float/0/float, max_steps:int/0/int · returned function · level recorded 2026-09-22
init_dct_basis scene/deform_model.py ran · honoured contract no licence file found · pointer only · 3af2cb1046724986 · report fixture: signature num_basis:int/0/int, num_frames:int/0/int · returned Tensor · level recorded 2026-09-22
skew in 21 papers scene/deform_model.py ran · honoured contract fingerprinted no licence file found · pointer only · 12e2c2cbe5064e7b · report fixture: signature w:Tensor/2/float · returned Tensor · level recorded 2026-09-22
to_homogenous scene/deform_model.py ran · honoured contract fingerprinted no licence file found · pointer only · d435e31a56bcb01d · report fixture: signature v:Tensor/2/float · returned Tensor · level recorded 2026-09-22
FlowHead in 7 papers scene/deform_model.py unverified no licence file found · pointer only · 46ae9697f6cb588d · report
GeneralMLP scene/deform_model.py unverified no licence file found · pointer only · 8e0bd50736c1783b · report
SplatFields scene/deform_model.py unverified no licence file found · pointer only · ceb4d941a3940ae6 · report
SplatFieldsModel scene/deform_model.py unverified no licence file found · pointer only · c83e03b69ec8e76a · report
exp_se3 scene/deform_model.py unverified no licence file found · pointer only · e79d60c41a96e8e9 · report
rp_to_se3 in 5 papers scene/deform_model.py unverified no licence file found · pointer only · a99a761118ab28bc · report
scaled_exp_se3 scene/deform_model.py unverified no licence file found · pointer only · e4bf8d7bbc32d686 · report
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
searchForMaxIteration repository not located ran · honoured contract licence of this copy not recorded · c1e505eec9aae423 · report fixture: signature folder:str/0/str · returned int · level recorded 2026-09-22

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. 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for SplatFields (graph method: SplatFields). 19 bricks; individually on a fixture: 12 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 5 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. SplatFieldsModel entry · level 0 · unverified · c83e03b69ec8e76a
  2. SplatFields model · level 0 · unverified · ceb4d941a3940ae6
  3. get_expon_lr_func helper · level 1 · ran · our draft was wrong · 7325f65ee1e29543
  4. searchForMaxIteration helper · level 1 · ran · honoured contract · c1e505eec9aae423
  5. FlowHead helper · level 0 · unverified · 46ae9697f6cb588d
  6. GeneralMLP helper · level 0 · unverified · 8e0bd50736c1783b
  7. get_embedder helper · level 1 · ran · our draft was wrong · 8d68829e9ebe344d
  8. SirenMLP helper · level 1 · ran · a10256972809fc78
  9. exp_se3 helper · level 0 · unverified · e79d60c41a96e8e9
  10. from_homogenous helper · level 1 · ran · honoured contract · 5097b2d841c17f14
  11. init_dct_basis helper · level 1 · ran · honoured contract · 3af2cb1046724986
  12. scaled_exp_se3 helper · level 0 · unverified · e4bf8d7bbc32d686
  13. to_homogenous helper · level 1 · ran · honoured contract · d435e31a56bcb01d
  14. Linear helper · level 1 · ran · ff83d06e72a107a2
  15. Embedder helper · level 1 · ran · e61cc7bddc7d86e5
  16. Sine helper · level 1 · ran · 08438c622b9a2549
  17. exp_so3 helper · level 1 · ran; the contract check could not run (RAISES) · 8bec3035faa583da
  18. rp_to_se3 helper · level 0 · unverified · a99a761118ab28bc
  19. skew helper · level 1 · ran · honoured contract · 12e2c2cbe5064e7b

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="2409.11211") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3DGS4D reconstruction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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