Papers › On Scaling Up 3D Gaussian Splatting Training

On Scaling Up 3D Gaussian Splatting Training

26 Jun 2024arXiv:2406.18533archive 2025-07-28

Hexu Zhao, Haoyang Weng, Daohan Lu, Ang Li, Jinyang Li, Aurojit Panda, Saining Xie

3D Gaussian Splatting (3DGS) is increasingly popular for 3D reconstruction due to its superior visual quality and rendering speed. However, 3DGS training currently occurs on a single GPU, limiting its ability to handle high-resolution and large-scale 3D reconstruction tasks due to memory constraints. We introduce Grendel, a distributed system designed to partition 3DGS parameters and parallelize computation across multiple GPUs. As each Gaussian affects a small, dynamic subset of rendered pixels, Grendel employs sparse all-to-all communication to transfer the necessary Gaussians to pixel partitions and performs dynamic load balancing. Unlike existing 3DGS systems that train using one camera view image at a time, Grendel supports batched training with multiple views. We explore various optimization hyperparameter scaling strategies and find that a simple sqrt(batch size) scaling rule is highly effective. Evaluations using large-scale, high-resolution scenes show that Grendel enhances rendering quality by scaling up 3DGS parameters across multiple GPUs. On the Rubble dataset, we achieve a test PSNR of 27.28 by distributing 40.4 million Gaussians across 16 GPUs, compared to a PSNR of 26.28 using 11.2 million Gaussians on a single GPU. Grendel is an open-source project available at: https://github.com/nyu-systems/Grendel-GS

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 Grendel, 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='Grendel') (how to connect); the free check have('2406.18533') needs no token.

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

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 11 ran (3 with no instrument failure; 8 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 11 samples that ran have no recorded date.

nyu-systems/grendel-gs officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 11 ran (8 instrument-failed) · 4 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

15 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 4 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.

2ran · honoured contract
8ran · our draft was wrong
1ran
4unverified

Licence: 0 of the 15 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 nyu-systems/grendel-gs. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

nyu-systems/grendel-gs official repository 15 samples, 11 ran (8 instrument-failed) · 4 unverified
extract_data_from_list_by_iteration analyze_statistic.py ran · our draft was wrong Apache-2.0 (permissive) · de64974a9b0e5a6e · report fixture: signature data_list:list/1/dict, iteration:int/0/int · returned dict · level recorded 2026-09-24
gaussian in 218 papers
census: 8 implementations from 9 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
utils/loss_utils.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · c56b7ef16f309a45 · report fixture: signature window_size:int/0/int, sigma:float/0/float · returned Tensor · level recorded, date not recorded
get_sparse_ids scene/gaussian_model.py ran · our draft was wrong Apache-2.0 (permissive) · 0e227be86333f793 · report fixture: signature tensors:list/1/Tensor · returned Tensor · level recorded 2026-09-24
get_suffix_in_folder examples/mip360/analyze_results.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 09cc5d1fc556fd75 · report fixture: signature folder:str/0/str · returned list · level recorded, date not recorded
get_suffix_in_folder analyze.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · caffb775ed8f26f5 · report fixture: signature folder:str/0/str · returned list · level recorded 2026-09-24
get_suffix_in_folder analyze_statistic.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 75db674c376d6b94 · report fixture: signature folder:str/0/str · returned list · level recorded 2026-09-24
get_test_psnr_at_iterations examples/mip360/analyze_results.py ran · our draft was wrong Apache-2.0 (permissive) · bb6cf981751aceff · report fixture: signature expe_folder:str/0/str, iterations:list/1/int · returned list · level recorded, date not recorded
get_touched_tile_rect gaussian_renderer/loss_distribution.py ran · our draft was wrong Apache-2.0 (permissive) · a269001c6b211066 · report fixture: signature touched_locally:Tensor/2/float · returned tuple · level recorded 2026-09-24
l1_loss in 149 papers
census: 3 implementations from 7 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
utils/loss_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · ac0e42d6fbcfbbe6 · report fixture: signature network_output:Tensor/2/float, gt:Tensor/2/float · returned Tensor · level recorded 2026-09-24
l2_loss in 136 papers utils/loss_utils.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 8c3b0f873ba11813 · report fixture: signature network_output:Tensor/2/float, gt:Tensor/2/float · returned Tensor · level recorded 2026-09-24
readImages in 71 papers metrics.py ran Apache-2.0 (permissive) · 3a23e82389fcee75 · report fixture: signature renders_dir:PosixPath/0/?, gt_dir:PosixPath/0/? · returned tuple · level recorded 2026-09-24
get_n3dgs_list_from_log analyze.py unverified Apache-2.0 (permissive) · e9c443ad173f5083 · report
get_n3dgs_list_per_rank_from_log analyze.py unverified Apache-2.0 (permissive) · b29a042c599e4a3c · report
get_running_time_at_iterations examples/mip360/analyze_results.py unverified Apache-2.0 (permissive) · f3e3ea18903f6696 · report
read_file in 112 papers analyze_statistic.py unverified Apache-2.0 (permissive) · 93438892eb42697d · 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. 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.

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

generated Assembly for Grendel (graph method: Grendel), 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. calculate_division_points entry · level 2 · ran · dfc8e9285d02d6c6583660a213053d1b2ea05a1cd0a39d9695b7d6007b14dec7

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="2406.18533") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Reconstruction3DGS

1 archive task tag without a task page not shown.

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