Papers › Hierarchical Aggregation for 3D Instance Segmentation

Hierarchical Aggregation for 3D Instance Segmentation

5 Aug 2021ICCV 2021 10arXiv:2108.02350archive 2025-07-28

Shaoyu Chen, Jiemin Fang, Qian Zhang, Wenyu Liu, Xinggang Wang

Instance segmentation on point clouds is a fundamental task in 3D scene perception. In this work, we propose a concise clustering-based framework named HAIS, which makes full use of spatial relation of points and point sets. Considering clustering-based methods may result in over-segmentation or under-segmentation, we introduce the hierarchical aggregation to progressively generate instance proposals, i.e., point aggregation for preliminarily clustering points to sets and set aggregation for generating complete instances from sets. Once the complete 3D instances are obtained, a sub-network of intra-instance prediction is adopted for noisy points filtering and mask quality scoring. HAIS is fast (only 410ms per frame) and does not require non-maximum suppression. It ranks 1st on the ScanNet v2 benchmark, achieving the highest 69.9% AP50 and surpassing previous state-of-the-art (SOTA) methods by a large margin. Besides, the SOTA results on the S3DIS dataset validate the good generalization ability. Code will be available at https://github.com/hustvl/HAIS.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

hustvl/HAIS officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset (arXiv:2203.09065; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Instance SegmentationClusteringInstance SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Instance Segmentation S3DIS HAIS mCov 67.0 #13 of 21 Archive leaderboard report
3D Instance Segmentation S3DIS HAIS mPrec 73.2 #13 of 21 Archive leaderboard report
3D Instance Segmentation S3DIS HAIS mRec 69.4 #13 of 21 Archive leaderboard report
3D Instance Segmentation S3DIS HAIS mWCov 70.4 #13 of 21 Archive leaderboard report
3D Instance Segmentation STPLS3D HAIS AP 35.1 #8 of 9 Archive leaderboard report
3D Instance Segmentation STPLS3D HAIS AP25 52.8 #8 of 9 Archive leaderboard report
3D Instance Segmentation STPLS3D HAIS AP50 46.7 #8 of 9 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) HAIS mAP 45.7 #15 of 32 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) HAIS mAP @ 50 69.9 #15 of 32 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