Papers › WildGaussians: 3D Gaussian Splatting in the Wild

WildGaussians: 3D Gaussian Splatting in the Wild

11 Jul 2024arXiv:2407.08447archive 2025-07-28

Jonas Kulhanek, Songyou Peng, Zuzana Kukelova, Marc Pollefeys, Torsten Sattler

While the field of 3D scene reconstruction is dominated by NeRFs due to their photorealistic quality, 3D Gaussian Splatting (3DGS) has recently emerged, offering similar quality with real-time rendering speeds. However, both methods primarily excel with well-controlled 3D scenes, while in-the-wild data - characterized by occlusions, dynamic objects, and varying illumination - remains challenging. NeRFs can adapt to such conditions easily through per-image embedding vectors, but 3DGS struggles due to its explicit representation and lack of shared parameters. To address this, we introduce WildGaussians, a novel approach to handle occlusions and appearance changes with 3DGS. By leveraging robust DINO features and integrating an appearance modeling module within 3DGS, our method achieves state-of-the-art results. We demonstrate that WildGaussians matches the real-time rendering speed of 3DGS while surpassing both 3DGS and NeRF baselines in handling in-the-wild data, all within a simple architectural framework.

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="2407.08447")

Code

Syntology Ran 16 of 21 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 11 ran with no contract checked.

By repository: official repository: 21 samples from 1 repository, 16 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jkulhanek/wild-gaussians officialmentioned on GitHubNOASSERTION 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

21 samples harvested; 16 ran; 2 honoured the contract we drafted; 5 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
2ran · our draft was wrong
1ran · fixture could not drive it
11ran
5unverified

Licence: 21 of the 21 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 jkulhanek/wild-gaussians. “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.

assert_not_none jkulhanek/wild-gaussians/wildgaussians/method.py official repository ran fingerprinted licence not identified · pointer only · e2fb6187962474ce · report
assert_not_none jkulhanek/wild-gaussians/wildgaussians/evaluation.py official repository ran fingerprinted licence not identified · pointer only · 7db796cdd6ad22ac · report
assert_not_none jkulhanek/wild-gaussians/wildgaussians/utils.py official repository ran fingerprinted licence not identified · pointer only · 3343ef634c1e8a16 · report
dmpix_ssim jkulhanek/wild-gaussians/wildgaussians/evaluation.py official repository ran licence not identified · pointer only · 65af632cd1b474cf · report
drop_add_residual_stochastic_depth jkulhanek/wild-gaussians/wildgaussians/dinov2.py official repository ran licence not identified · pointer only · bd91e9a4fc420313 · report
drop_path jkulhanek/wild-gaussians/wildgaussians/dinov2.py official repository ran · fixture could not drive it no licence file found · pointer only · c157f5b112b3a392 · report
make_2tuple jkulhanek/wild-gaussians/wildgaussians/dinov2.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 3c04490a215299f2 · report
pad_poses jkulhanek/wild-gaussians/wildgaussians/datasets/_common.py official repository ran fingerprinted licence not identified · pointer only · 2980b569c9e6ba85 · report
read_cameras_text jkulhanek/wild-gaussians/wildgaussians/datasets/_colmap_utils.py official repository ran · our draft was wrong no licence file found · pointer only · 8a38e306ff4c5b42 · report
read_next_bytes jkulhanek/wild-gaussians/wildgaussians/datasets/_colmap_utils.py official repository ran · honoured contract no licence file found · pointer only · 56858e04e6fdb2ff · report
rotation_matrix jkulhanek/wild-gaussians/wildgaussians/datasets/_common.py official repository ran licence not identified · pointer only · d61d33fc47413d81 · report
spatial_average jkulhanek/wild-gaussians/wildgaussians/_metrics_lpips.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 29e5e72bcd006dcd · report
srgb_to_linear jkulhanek/wild-gaussians/wildgaussians/utils.py official repository ran fingerprinted licence not identified · pointer only · e4806ed5a1eb8585 · report
ssim jkulhanek/wild-gaussians/wildgaussians/evaluation.py official repository ran licence not identified · pointer only · 328e135581413fe7 · report
unpad_poses jkulhanek/wild-gaussians/wildgaussians/datasets/_common.py official repository ran fingerprinted licence not identified · pointer only · e1e33ba4f452b9ac · report
upsample jkulhanek/wild-gaussians/wildgaussians/_metrics_lpips.py official repository ran licence not identified · pointer only · 79a2a8a370c460a5 · report
convert_image_dtype jkulhanek/wild-gaussians/wildgaussians/method.py official repository unverified no licence file found · pointer only · aae353a107ad40dc · report
get_torch_checkpoint_sha jkulhanek/wild-gaussians/wildgaussians/method.py official repository unverified licence not identified · pointer only · f3570c44fceb6d12 · report
load_phototourism_dataset jkulhanek/wild-gaussians/wildgaussians/datasets/phototourism.py official repository unverified licence not identified · pointer only · e8bd393ac5b12214 · report
normalize_tensor jkulhanek/wild-gaussians/wildgaussians/_metrics_lpips.py official repository unverified no licence file found · pointer only · 61221a9686133a8c · report
read_cameras_binary jkulhanek/wild-gaussians/wildgaussians/datasets/_colmap_utils.py official repository unverified no licence file found · pointer only · 4a20cdd355703af3 · report

Tasks

3D Scene Reconstruction3DGSNeRF

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionDINODense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSPEEDSoftmaxVision Transformer

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