Papers › Weakly Supervised 3D Open-vocabulary Segmentation

Weakly Supervised 3D Open-vocabulary Segmentation

23 May 2023NeurIPS 2023 11arXiv:2305.14093archive 2025-07-28

Kunhao Liu, Fangneng Zhan, Jiahui Zhang, Muyu Xu, Yingchen Yu, Abdulmotaleb El Saddik, Christian Theobalt, Eric Xing, Shijian Lu

Open-vocabulary segmentation of 3D scenes is a fundamental function of human perception and thus a crucial objective in computer vision research. However, this task is heavily impeded by the lack of large-scale and diverse 3D open-vocabulary segmentation datasets for training robust and generalizable models. Distilling knowledge from pre-trained 2D open-vocabulary segmentation models helps but it compromises the open-vocabulary feature as the 2D models are mostly finetuned with close-vocabulary datasets. We tackle the challenges in 3D open-vocabulary segmentation by exploiting pre-trained foundation models CLIP and DINO in a weakly supervised manner. Specifically, given only the open-vocabulary text descriptions of the objects in a scene, we distill the open-vocabulary multimodal knowledge and object reasoning capability of CLIP and DINO into a neural radiance field (NeRF), which effectively lifts 2D features into view-consistent 3D segmentation. A notable aspect of our approach is that it does not require any manual segmentation annotations for either the foundation models or the distillation process. Extensive experiments show that our method even outperforms fully supervised models trained with segmentation annotations in certain scenes, suggesting that 3D open-vocabulary segmentation can be effectively learned from 2D images and text-image pairs. Code is available at \url{https://github.com/Kunhao-Liu/3D-OVS}.

PaperPDFConference PDFCodeCode 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="2305.14093")

Code

Syntology Ran 11 of 14 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 9 ran with no contract checked.

By repository: official repository: 14 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.

kunhao-liu/3d-ovs officialmentioned in papermentioned on GitHubpytorchMIT 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

14 samples harvested; 11 ran; 0 honoured the contract we drafted; 3 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.

1ran · our draft was wrong
1ran · fixture could not drive it
9ran
3unverified

Licence: 0 of the 14 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 Kunhao-Liu/3D-OVS. “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.

OctreeRender_trilinear_fast Kunhao-Liu/3D-OVS/renderer.py official repository ran MIT (permissive) · 945933374c5e3cbf · report
OctreeRender_trilinear_fast_depth Kunhao-Liu/3D-OVS/renderer.py official repository ran MIT (permissive) · eae018b803b70a00 · report
eval_sh Kunhao-Liu/3D-OVS/models/sh.py official repository ran MIT (permissive) · db95ecdf5d4abe6b · report
eval_sh_bases Kunhao-Liu/3D-OVS/models/sh.py official repository ran · fixture could not drive it MIT (permissive) · caa9e209a9083a0f · report
init_log Kunhao-Liu/3D-OVS/funcs.py official repository ran MIT (permissive) · dc510fe4f2261490 · report
positional_encoding Kunhao-Liu/3D-OVS/models/tensorBase.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 11a10efa60767162 · report
raw2alpha Kunhao-Liu/3D-OVS/models/tensorBase.py official repository ran fingerprinted MIT (permissive) · c1acffa981204fee · report
sharpness Kunhao-Liu/3D-OVS/dataLoader/colmap2nerf.py official repository ran MIT (permissive) · 521893f959a2ef80 · report
variance_of_laplacian Kunhao-Liu/3D-OVS/dataLoader/colmap2nerf.py official repository ran MIT (permissive) · 6ccb6c10eee60ba1 · report
visualize_depth Kunhao-Liu/3D-OVS/funcs.py official repository ran MIT (permissive) · 5346431312bff754 · report
visualize_depth_numpy Kunhao-Liu/3D-OVS/funcs.py official repository ran MIT (permissive) · c775698c33cfa2de · report
SHRender Kunhao-Liu/3D-OVS/models/tensorBase.py official repository unverified MIT (permissive) · 3a530f556e40d9c0 · report
evaluation Kunhao-Liu/3D-OVS/renderer.py official repository unverified MIT (permissive) · 9a9881451ca96ede · report
qvec2rotmat Kunhao-Liu/3D-OVS/dataLoader/colmap2nerf.py official repository unverified MIT (permissive) · 6ce64cf0fbcd6bb1 · report

Tasks

NeRFSegmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionCLIPDINODense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision 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