Research map / Point clouds / Segmentation and detection
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use RandLA-Net instead of KPConv | Semantic3D reduced-8 · Semantic3D reduced-8 | mIoU (%): 74.6 -> 77.4 | Helped |
| Use RandLA-Net instead of RangeNet53++ | SemanticKITTI · SemanticKITTI online single scan evaluation | mIoU (%): 52.2 -> 53.9 | Helped |
| Use RandLA-Net instead of KPConv | S3DIS · S3DIS 6-fold cross-validation | mIoU (%): 70.6 -> 70.0 | Hurt |
| Use RandLA-Net for inference | SemanticKITTI Sequence 08 · SemanticKITTI Sequence 08 | Total time (seconds): 717 -> 185 | Helped |
| Add local spatial encoding (ablation) | RandLA-Net · SemanticKITTI validation Sequence 08 | mIoU (%): 49.8 -> 57.1 | Helped |
| Use attentive pooling instead of max pooling (ablation) | RandLA-Net · SemanticKITTI validation Sequence 08 | mIoU (%): 55.2 -> 57.1 | Helped |
| Use attentive pooling instead of mean pooling (ablation) | RandLA-Net · SemanticKITTI validation Sequence 08 | mIoU (%): 53.4 -> 57.1 | Helped |
| Use attentive pooling instead of sum pooling (ablation) | RandLA-Net · SemanticKITTI validation Sequence 08 | mIoU (%): 54.3 -> 57.1 | Helped |
| Chain two aggregation units rather than one in each dilated residual block (ablation) | RandLA-Net · SemanticKITTI validation Sequence 08 | mIoU (%): 48.8 -> 57.1 | Helped |
| Increase the dilated residual block from two to three aggregation units (ablation) | RandLA-Net · SemanticKITTI validation Sequence 08 | mIoU (%): 54.3 -> 51.1 | Hurt |
| Encode center and neighbor coordinates, relative position, and Euclidean distance in LocSE (ablation) | RandLA-Net LocSE · SemanticKITTI | mIoU (%): 53.6 -> 54.3 | Helped |
| Add relative position to center and neighbor coordinates in LocSE (ablation) | RandLA-Net LocSE · SemanticKITTI | mIoU (%): 49.1 -> 53.6 | Helped |
Closest papers by meaning
- DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis (CVPR 2025 · similarity 0.90)
- Point-MoE: Large-Scale Multi-Dataset Training with Mixture-of-Experts for 3D Semantic Segmentation (ICLR 2026 · similarity 0.89)
- Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation (CVPR 2023 · similarity 0.89)
- Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges (CVPR 2021 · similarity 0.89)
- Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding (CVPR 2024 · similarity 0.88)
- Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.