TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Efficient 3D Semantic Segmentation with Superpoint Transfo...

Efficient 3D Semantic Segmentation with Superpoint Transformer

Damien Robert, Hugo Raguet, Loic Landrieu

2023-06-13ICCV 2023 1Semantic Segmentation3D Semantic Segmentation
PaperPDFCode(official)

Abstract

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.

Results

TaskDatasetMetricValueModel
Semantic SegmentationS3DIS Area5mAcc77.3Superpoint Transformer
Semantic SegmentationS3DIS Area5mIoU68.9Superpoint Transformer
Semantic SegmentationS3DIS Area5oAcc89.5Superpoint Transformer
Semantic SegmentationS3DISMean IoU76Superpoint Transformer
Semantic SegmentationS3DISParams (M)0.212Superpoint Transformer
Semantic SegmentationS3DISmAcc85.8Superpoint Transformer
Semantic SegmentationS3DISmIoU76Superpoint Transformer
Semantic SegmentationS3DISoAcc90.4Superpoint Transformer
Semantic SegmentationDALESOverall Accuracy97.5Superpoint Transformer
Semantic SegmentationDALESmIoU79.6Superpoint Transformer
Semantic SegmentationKITTI-360miou Val63.5Superpoint Transformer
Semantic SegmentationS3DISmAcc85.8Superpoint Transformer
Semantic SegmentationS3DISmIoU (6-Fold)76Superpoint Transformer
3D Semantic SegmentationDALESOverall Accuracy97.5Superpoint Transformer
3D Semantic SegmentationDALESmIoU79.6Superpoint Transformer
3D Semantic SegmentationKITTI-360miou Val63.5Superpoint Transformer
3D Semantic SegmentationS3DISmAcc85.8Superpoint Transformer
3D Semantic SegmentationS3DISmIoU (6-Fold)76Superpoint Transformer
10-shot image generationS3DIS Area5mAcc77.3Superpoint Transformer
10-shot image generationS3DIS Area5mIoU68.9Superpoint Transformer
10-shot image generationS3DIS Area5oAcc89.5Superpoint Transformer
10-shot image generationS3DISMean IoU76Superpoint Transformer
10-shot image generationS3DISParams (M)0.212Superpoint Transformer
10-shot image generationS3DISmAcc85.8Superpoint Transformer
10-shot image generationS3DISmIoU76Superpoint Transformer
10-shot image generationS3DISoAcc90.4Superpoint Transformer
10-shot image generationDALESOverall Accuracy97.5Superpoint Transformer
10-shot image generationDALESmIoU79.6Superpoint Transformer
10-shot image generationKITTI-360miou Val63.5Superpoint Transformer
10-shot image generationS3DISmAcc85.8Superpoint Transformer
10-shot image generationS3DISmIoU (6-Fold)76Superpoint Transformer

Related Papers

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction2025-07-21DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model2025-07-17SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation2025-07-17Unified Medical Image Segmentation with State Space Modeling Snake2025-07-17A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique2025-07-17SAMST: A Transformer framework based on SAM pseudo label filtering for remote sensing semi-supervised semantic segmentation2025-07-16Tomato Multi-Angle Multi-Pose Dataset for Fine-Grained Phenotyping2025-07-15U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV2025-07-15