Papers › Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding

Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding

29 Nov 2024arXiv:2411.19551archive 2025-07-28

Wenbo Zhang, Lu Zhang, Ping Hu, Liqian Ma, Yunzhi Zhuge, Huchuan Lu

Injecting semantics into 3D Gaussian Splatting (3DGS) has recently garnered significant attention. While current approaches typically distill 3D semantic features from 2D foundational models (e.g., CLIP and SAM) to facilitate novel view segmentation and semantic understanding, their heavy reliance on 2D supervision can undermine cross-view semantic consistency and necessitate complex data preparation processes, therefore hindering view-consistent scene understanding. In this work, we present FreeGS, an unsupervised semantic-embedded 3DGS framework that achieves view-consistent 3D scene understanding without the need for 2D labels. Instead of directly learning semantic features, we introduce the IDentity-coupled Semantic Field (IDSF) into 3DGS, which captures both semantic representations and view-consistent instance indices for each Gaussian. We optimize IDSF with a two-step alternating strategy: semantics help to extract coherent instances in 3D space, while the resulting instances regularize the injection of stable semantics from 2D space. Additionally, we adopt a 2D-3D joint contrastive loss to enhance the complementarity between view-consistent 3D geometry and rich semantics during the bootstrapping process, enabling FreeGS to uniformly perform tasks such as novel-view semantic segmentation, object selection, and 3D object detection. Extensive experiments on LERF-Mask, 3D-OVS, and ScanNet datasets demonstrate that FreeGS performs comparably to state-of-the-art methods while avoiding the complex data preprocessing workload. Our code is publicly available at https://github.com/wb014/FreeGS.

PaperPDFCodeCode Syntology ran

In Syntology 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="2411.19551")

Code

Syntology Ran 5 of 12 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

wb014/FreeGS officialmentioned in papermentioned on GitHubpytorch 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

12 samples harvested; 5 ran; 2 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · our draft was wrong
2ran
7unverified

Licence: 12 of the 12 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 wb014/FreeGS. “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.

get_expon_lr_func wb014/FreeGS/utils/general_utils.py official repository ran · our draft was wrong no licence file found · pointer only · 7325f65ee1e29543 · report
inverse_sigmoid wb014/FreeGS/utils/general_utils.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · b488da571728b636 · report
l1_loss wb014/FreeGS/utils/loss_utils.py official repository ran fingerprinted no licence file found · pointer only · ac0e42d6fbcfbbe6 · report
l2_loss wb014/FreeGS/utils/loss_utils.py official repository ran fingerprinted no licence file found · pointer only · 8c3b0f873ba11813 · report
read_next_bytes wb014/FreeGS/scene/colmap_loader.py official repository ran · honoured contract no licence file found · pointer only · 56858e04e6fdb2ff · report
PILtoTorch wb014/FreeGS/utils/general_utils.py official repository unverified no licence file found · pointer only · 301bd8c9fc8769e3 · report
dilate wb014/FreeGS/train_freegs.py official repository unverified no licence file found · pointer only · ef11a6b3782463a1 · report
distCUDA2 wb014/FreeGS/scene/gaussian_model.py official repository unverified no licence file found · pointer only · 1420b25f81e3e725 · report
generate_unique_colors wb014/FreeGS/train_freegs.py official repository unverified no licence file found · pointer only · 2ffdf340fdd5e487 · report
ins_l1_loss wb014/FreeGS/utils/loss_utils.py official repository unverified no licence file found · pointer only · 28862fced4963b57 · report
qvec2rotmat wb014/FreeGS/scene/colmap_loader.py official repository unverified no licence file found · pointer only · 6ce64cf0fbcd6bb1 · report
rotmat2qvec wb014/FreeGS/scene/colmap_loader.py official repository unverified no licence file found · pointer only · 659bc4e7e63ed8f9 · report

Tasks

3D Object Detection3D geometry3DGSClusteringObject DetectionScene UnderstandingSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ADOPTCLIP

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