Papers › MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation

MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation

4 Nov 2024arXiv:2411.01781archive 2025-07-28

Duc Dang Trung Tran, Byeongkeun Kang, Yeejin Lee

Recently, transformer-based techniques incorporating superpoints have become prevalent in 3D instance segmentation. However, they often encounter an over-segmentation problem, especially noticeable with large objects. Additionally, unreliable mask predictions stemming from superpoint mask prediction further compound this issue. To address these challenges, we propose a novel framework called MSTA3D. It leverages multi-scale feature representation and introduces a twin-attention mechanism to effectively capture them. Furthermore, MSTA3D integrates a box query with a box regularizer, offering a complementary spatial constraint alongside semantic queries. Experimental evaluations on ScanNetV2, ScanNet200 and S3DIS datasets demonstrate that our approach surpasses state-of-the-art 3D instance segmentation methods.

PaperPDFConference PDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

3D Instance SegmentationInstance SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Instance Segmentation S3DIS MSTA3D AP@50 70.0 #6 of 21 Archive leaderboard report
3D Instance Segmentation S3DIS MSTA3D mPrec 80.6 #6 of 21 Archive leaderboard report
3D Instance Segmentation S3DIS MSTA3D mRec 70.1 #6 of 21 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) MSTA3D mAP 56.9 #5 of 32 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) MSTA3D mAP @ 50 79.5 #5 of 32 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) MSTA3D mAP@25 87.9 #5 of 32 Archive leaderboard report
3D Instance Segmentation ScanNet(v2) MSTA3D mRec 74.1 #5 of 32 Archive leaderboard report
3D Instance Segmentation ScanNet200 MSTA3D mAP 26.2 #3 of 5 Archive leaderboard report
3D Instance Segmentation ScanNet200 MSTA3D mAP@25 40.1 #3 of 5 Archive leaderboard report
3D Instance Segmentation ScanNet200 MSTA3D mAP@50 35.2 #3 of 5 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