Papers › 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation
3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation
Francis Engelmann, Martin Bokeloh, Alireza Fathi, Bastian Leibe, Matthias Nießner
We present 3D-MPA, a method for instance segmentation on 3D point clouds. Given an input point cloud, we propose an object-centric approach where each point votes for its object center. We sample object proposals from the predicted object centers. Then, we learn proposal features from grouped point features that voted for the same object center. A graph convolutional network introduces inter-proposal relations, providing higher-level feature learning in addition to the lower-level point features. Each proposal comprises a semantic label, a set of associated points over which we define a foreground-background mask, an objectness score and aggregation features. Previous works usually perform non-maximum-suppression (NMS) over proposals to obtain the final object detections or semantic instances. However, NMS can discard potentially correct predictions. Instead, our approach keeps all proposals and groups them together based on the learned aggregation features. We show that grouping proposals improves over NMS and outperforms previous state-of-the-art methods on the tasks of 3D object detection and semantic instance segmentation on the ScanNetV2 benchmark and the S3DIS dataset.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Instance Segmentation | S3DIS | 3D-MPA | mPrec | 66.7 | #16 of 21 | Archive leaderboard | report |
| 3D Instance Segmentation | S3DIS | 3D-MPA | mRec | 64.1 | #16 of 21 | Archive leaderboard | report |
| 3D Instance Segmentation | ScanNet(v2) | 3D-MPA | mAP | 35.3 | #22 of 32 | Archive leaderboard | report |
| 3D Instance Segmentation | ScanNet(v2) | 3D-MPA | mAP @ 50 | 59.1 | #22 of 32 | Archive leaderboard | report |
| 3D Instance Segmentation | ScanNet(v2) | 3D-MPA | mRec | 61.1 | #22 of 32 | Archive leaderboard | report |
| 3D Object Detection | ScanNetV2 | 3D-MPA | mAP@0.25 | 64.2 | #22 of 33 | Archive leaderboard | report |
| 3D Object Detection | ScanNetV2 | 3D-MPA | mAP@0.5 | 49.2 | #22 of 33 | Archive leaderboard | report |
| 3D Semantic Instance Segmentation | ScanNetV2 | 3D-MPA | mAP@0.50 | 61.1 | #1 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