Papers › OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation

OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation

1 Sep 2023arXiv:2309.00616archive 2025-07-28

Zhening Huang, Xiaoyang Wu, Xi Chen, Hengshuang Zhao, Lei Zhu, Joan Lasenby

In this work, we introduce OpenIns3D, a new 3D-input-only framework for 3D open-vocabulary scene understanding. The OpenIns3D framework employs a "Mask-Snap-Lookup" scheme. The "Mask" module learns class-agnostic mask proposals in 3D point clouds, the "Snap" module generates synthetic scene-level images at multiple scales and leverages 2D vision-language models to extract interesting objects, and the "Lookup" module searches through the outcomes of "Snap" to assign category names to the proposed masks. This approach, yet simple, achieves state-of-the-art performance across a wide range of 3D open-vocabulary tasks, including recognition, object detection, and instance segmentation, on both indoor and outdoor datasets. Moreover, OpenIns3D facilitates effortless switching between different 2D detectors without requiring retraining. When integrated with powerful 2D open-world models, it achieves excellent results in scene understanding tasks. Furthermore, when combined with LLM-powered 2D models, OpenIns3D exhibits an impressive capability to comprehend and process highly complex text queries that demand intricate reasoning and real-world knowledge. Project page: https://zheninghuang.github.io/OpenIns3D/

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="2309.00616")

Code

Syntology Ran 1 of 3 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 3 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Pointcept/OpenIns3D officialmentioned 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

3 samples harvested; 1 ran; 0 honoured the contract we drafted; 2 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
2unverified

Licence: 0 of the 3 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 Pointcept/OpenIns3D. “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.

openworld_recognition Pointcept/OpenIns3D/openins3d/evaluation/evaluate.py official repository ran · our draft was wrong MIT (permissive) · 5c088f6494146a68 · report
compute_averages Pointcept/OpenIns3D/openins3d/evaluation/evaluate.py official repository unverified MIT (permissive) · 1c7cec949d42c66b · report
evaluate_matches Pointcept/OpenIns3D/openins3d/evaluation/evaluate.py official repository unverified MIT (permissive) · c26919e3aa4ef5d2 · report

Tasks

3D Open-Vocabulary Instance Segmentation3D Open-Vocabulary Object DetectionInstance SegmentationObject DetectionOpen Vocabulary Object DetectionScene UnderstandingSemantic SegmentationZero-shot 3D Point Cloud Classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Open-Vocabulary Instance Segmentation Replica OpenIns3D (with rgbd) mAP 21.1 #2 of 7 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation Replica OpenIns3D mAP 15.4 #4 of 7 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation S3DIS OpenIns3D AP50 Novel B6/N6 33.0 #4 of 4 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation S3DIS OpenIns3D AP50 Novel B8/N4 37.0 #4 of 4 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation STPLS3D OPENINS3D AP50 13.3 #1 of 3 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation ScanNet200 OpenIns3D AP Common 14.2 #4 of 6 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation ScanNet200 OpenIns3D AP Head 19.2 #4 of 6 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation ScanNet200 OpenIns3D AP Tail 14.2 #4 of 6 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation ScanNet200 OpenIns3D AP25 23.3 #4 of 6 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation ScanNet200 OpenIns3D AP50 20.6 #4 of 6 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation ScanNet200 OpenIns3D mAP 15.9 #4 of 6 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation ScanNet200 OpenIns3D (3d only) AP Common 6.5 #6 of 6 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation ScanNet200 OpenIns3D (3d only) AP Head 16.0 #6 of 6 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation ScanNet200 OpenIns3D (3d only) AP Tail 4.2 #6 of 6 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation ScanNet200 OpenIns3D (3d only) AP25 14.4 #6 of 6 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation ScanNet200 OpenIns3D (3d only) AP50 10.3 #6 of 6 Archive leaderboard report
3D Open-Vocabulary Instance Segmentation ScanNet200 OpenIns3D (3d only) mAP 8.8 #6 of 6 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.

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