</> Code with Papers by Syntology

Papers › Efficient 3D Semantic Segmentation with Superpoint Transformer

Efficient 3D Semantic Segmentation with Superpoint Transformer

13 Jun 2023ICCV 2023 1arXiv:2306.08045archive 2025-07-28

Damien Robert, Hugo Raguet, Loic Landrieu

We introduce a novel superpoint-based transformer architecture for efficient semantic segmentation of large-scale 3D scenes. Our method incorporates a fast algorithm to partition point clouds into a hierarchical superpoint structure, which makes our preprocessing 7 times faster than existing superpoint-based approaches. Additionally, we leverage a self-attention mechanism to capture the relationships between superpoints at multiple scales, leading to state-of-the-art performance on three challenging benchmark datasets: S3DIS (76.0% mIoU 6-fold validation), KITTI-360 (63.5% on Val), and DALES (79.6%). With only 212k parameters, our approach is up to 200 times more compact than other state-of-the-art models while maintaining similar performance. Furthermore, our model can be trained on a single GPU in 3 hours for a fold of the S3DIS dataset, which is 7x to 70x fewer GPU-hours than the best-performing methods. Our code and models are accessible at github.com/drprojects/superpoint_transformer.

PaperPDFConference PDFCode

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

Code

drprojects/superpoint_transformer 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 Semantic SegmentationSemantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Semantic Segmentation DALES Superpoint Transformer Model size 212K #2 of 9 Archive leaderboard report
3D Semantic Segmentation DALES Superpoint Transformer Overall Accuracy 97.5 #2 of 9 Archive leaderboard report
3D Semantic Segmentation DALES Superpoint Transformer mIoU 79.6 #2 of 9 Archive leaderboard report
3D Semantic Segmentation KITTI-360 Superpoint Transformer Model size 777K #7 of 8 Archive leaderboard report
3D Semantic Segmentation KITTI-360 Superpoint Transformer miou Val 63.5 #7 of 8 Archive leaderboard report
3D Semantic Segmentation S3DIS Superpoint Transformer mAcc 85.8 #5 of 6 Archive leaderboard report
3D Semantic Segmentation S3DIS Superpoint Transformer mIoU (6-Fold) 76.0 #5 of 6 Archive leaderboard report
Semantic Segmentation S3DIS Superpoint Transformer Mean IoU 76.0 #10 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Superpoint Transformer Number of params 0.212M #10 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Superpoint Transformer Params (M) 0.212 #10 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Superpoint Transformer mAcc 85.8 #10 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Superpoint Transformer mIoU 76.0 #10 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Superpoint Transformer oAcc 90.4 #10 of 54 Archive leaderboard report
Semantic Segmentation S3DIS Area5 Superpoint Transformer Number of params 212K #35 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 Superpoint Transformer mAcc 77.3 #35 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 Superpoint Transformer mIoU 68.9 #35 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 Superpoint Transformer oAcc 89.5 #35 of 61 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