Papers › SoftGroup for 3D Instance Segmentation on Point Clouds

SoftGroup for 3D Instance Segmentation on Point Clouds

3 Mar 2022CVPR 2022 1arXiv:2203.01509archive 2025-07-28

Thang Vu, Kookhoi Kim, Tung M. Luu, Xuan Thanh Nguyen, Chang D. Yoo

Existing state-of-the-art 3D instance segmentation methods perform semantic segmentation followed by grouping. The hard predictions are made when performing semantic segmentation such that each point is associated with a single class. However, the errors stemming from hard decision propagate into grouping that results in (1) low overlaps between the predicted instance with the ground truth and (2) substantial false positives. To address the aforementioned problems, this paper proposes a 3D instance segmentation method referred to as SoftGroup by performing bottom-up soft grouping followed by top-down refinement. SoftGroup allows each point to be associated with multiple classes to mitigate the problems stemming from semantic prediction errors and suppresses false positive instances by learning to categorize them as background. Experimental results on different datasets and multiple evaluation metrics demonstrate the efficacy of SoftGroup. Its performance surpasses the strongest prior method by a significant margin of +6.2% on the ScanNet v2 hidden test set and +6.8% on S3DIS Area 5 in terms of AP_50. SoftGroup is also fast, running at 345ms per scan with a single Titan X on ScanNet v2 dataset. The source code and trained models for both datasets are available at \url{https://github.com/thangvubk/SoftGroup.git}.

PaperPDFConference PDFCode

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

Code

thangvubk/softgroup 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

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

Tasks

3D Instance Segmentation3D Object DetectionInstance SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Instance Segmentation S3DIS SoftGroup AP@50 68.9 #9 of 21 Archive leaderboard report
3D Instance Segmentation S3DIS SoftGroup mAP 54.4 #9 of 21 Archive leaderboard report
3D Instance Segmentation S3DIS SoftGroup mCov 69.3 #9 of 21 Archive leaderboard report
3D Instance Segmentation S3DIS SoftGroup mPrec 75.3 #9 of 21 Archive leaderboard report
3D Instance Segmentation S3DIS SoftGroup mRec 69.8 #9 of 21 Archive leaderboard report
3D Instance Segmentation S3DIS SoftGroup mWCov 71.7 #9 of 21 Archive leaderboard report
3D Instance Segmentation STPLS3D SoftGroup AP 47.3 #6 of 9 Archive leaderboard report
3D Instance Segmentation STPLS3D SoftGroup AP25 71.4 #6 of 9 Archive leaderboard report
3D Instance Segmentation STPLS3D SoftGroup AP50 63.1 #6 of 9 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) SoftGroup mAP 50.4 #10 of 32 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) SoftGroup mAP @ 50 76.1 #10 of 32 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) SoftGroup mAP@25 86.5 #10 of 32 Archive leaderboard report
3D Object Detection ScanNetV2 SoftGroup mAP@0.25 71.6 #13 of 33 Archive leaderboard report
3D Object Detection ScanNetV2 SoftGroup mAP@0.5 59.4 #13 of 33 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