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 ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2406.18533")

Code

Syntology Ran 11 of 15 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong; 8 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nyu-systems/grendel-gs officialmentioned in papermentioned on GitHubpytorchApache-2.0 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; 1 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong
8ran
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. “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.

extract_data_from_list_by_iteration nyu-systems/grendel-gs/analyze_statistic.py official repository ran Apache-2.0 (permissive) · de64974a9b0e5a6e · report
gaussian nyu-systems/grendel-gs/utils/loss_utils.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · c56b7ef16f309a45 · report
get_sparse_ids nyu-systems/grendel-gs/scene/gaussian_model.py official repository ran Apache-2.0 (permissive) · 0e227be86333f793 · report
get_suffix_in_folder nyu-systems/Grendel-GS/examples/mip360/analyze_results.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 09cc5d1fc556fd75 · report
get_suffix_in_folder nyu-systems/grendel-gs/analyze.py official repository ran fingerprinted Apache-2.0 (permissive) · caffb775ed8f26f5 · report
get_suffix_in_folder nyu-systems/grendel-gs/analyze_statistic.py official repository ran fingerprinted Apache-2.0 (permissive) · 75db674c376d6b94 · report
get_test_psnr_at_iterations nyu-systems/Grendel-GS/examples/mip360/analyze_results.py official repository ran · our draft was wrong Apache-2.0 (permissive) · bb6cf981751aceff · report
get_touched_tile_rect nyu-systems/grendel-gs/gaussian_renderer/loss_distribution.py official repository ran Apache-2.0 (permissive) · a269001c6b211066 · report
l1_loss nyu-systems/grendel-gs/utils/loss_utils.py official repository ran fingerprinted Apache-2.0 (permissive) · ac0e42d6fbcfbbe6 · report
l2_loss nyu-systems/grendel-gs/utils/loss_utils.py official repository ran fingerprinted Apache-2.0 (permissive) · 8c3b0f873ba11813 · report
readImages nyu-systems/grendel-gs/metrics.py official repository ran Apache-2.0 (permissive) · 3a23e82389fcee75 · report
get_n3dgs_list_from_log nyu-systems/grendel-gs/analyze.py official repository unverified Apache-2.0 (permissive) · e9c443ad173f5083 · report
get_n3dgs_list_per_rank_from_log nyu-systems/grendel-gs/analyze.py official repository unverified Apache-2.0 (permissive) · b29a042c599e4a3c · report
get_running_time_at_iterations nyu-systems/Grendel-GS/examples/mip360/analyze_results.py official repository unverified Apache-2.0 (permissive) · f3e3ea18903f6696 · report
read_file nyu-systems/grendel-gs/analyze_statistic.py official repository unverified Apache-2.0 (permissive) · 93438892eb42697d · report

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