Papers › 3D Gaussian Splatting for Real-Time Radiance Field Rendering

3D Gaussian Splatting for Real-Time Radiance Field Rendering

8 Aug 2023arXiv:2308.04079archive 2025-07-28

Bernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George Drettakis

Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (>= 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.

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="2308.04079")

Code

Syntology Ran 6 of 10 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · honoured contract; 4 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

graphdeco-inria/gaussian-splatting officialpytorchNOASSERTION report
smbonilla/gaussianpancakes mentioned on GitHubpytorchNOASSERTION 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

10 samples harvested; 6 ran; 2 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.

2ran · honoured contract
4ran
4unverified

Licence: 10 of the 10 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 graphdeco-inria/gaussian-splatting. “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.

gaussian graphdeco-inria/gaussian-splatting/utils/loss_utils.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · c56b7ef16f309a45 · report
l1_loss graphdeco-inria/gaussian-splatting/utils/loss_utils.py official repository ran fingerprinted no licence file found · pointer only · ac0e42d6fbcfbbe6 · report
l2_loss graphdeco-inria/gaussian-splatting/utils/loss_utils.py official repository ran fingerprinted no licence file found · pointer only · 8c3b0f873ba11813 · report
normalize_activation graphdeco-inria/gaussian-splatting/lpipsPyTorch/modules/utils.py official repository ran fingerprinted no licence file found · pointer only · 1dab900b2adbe38e · report
readImages graphdeco-inria/gaussian-splatting/metrics.py official repository ran no licence file found · pointer only · cdd00787894554b5 · report
read_next_bytes graphdeco-inria/gaussian-splatting/utils/read_write_model.py official repository ran · honoured contract no licence file found · pointer only · 56858e04e6fdb2ff · report
get_network graphdeco-inria/gaussian-splatting/lpipsPyTorch/modules/networks.py official repository unverified no licence file found · pointer only · 07bd0da29c4dc7bb · report
get_state_dict graphdeco-inria/gaussian-splatting/lpipsPyTorch/modules/utils.py official repository unverified no licence file found · pointer only · b06f27c08cf5d0ca · report
read_cameras_binary graphdeco-inria/gaussian-splatting/utils/read_write_model.py official repository unverified no licence file found · pointer only · a10bf79d34938dbd · report
read_cameras_text graphdeco-inria/gaussian-splatting/utils/read_write_model.py official repository unverified no licence file found · pointer only · c424ebf4a6c32cbd · report

Tasks

Camera CalibrationNovel View Synthesis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Novel View Synthesis Mip-NeRF 360 3D Gaussian Splatting LPIPS 0.214 #5 of 14 Archive leaderboard report
Novel View Synthesis Mip-NeRF 360 3D Gaussian Splatting PSNR 27.21 #5 of 14 Archive leaderboard report
Novel View Synthesis Mip-NeRF 360 3D Gaussian Splatting SSIM 0.815 #5 of 14 Archive leaderboard report
Novel View Synthesis Tanks and Temples 3D Gaussian Splatting LPIPS 0.183 #7 of 10 Archive leaderboard report
Novel View Synthesis Tanks and Temples 3D Gaussian Splatting PSNR 23.14 #7 of 10 Archive leaderboard report
Novel View Synthesis Tanks and Temples 3D Gaussian Splatting SSIM 0.841 #7 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SPEED

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