Research map / Point clouds / Point cloud classification
PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling
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 |
|---|---|---|---|
| combine local and nonlocal feature learning instead of using only PNL (ablation) | PointASNL · ModelNet40 | overall accuracy: 90.1 -> 93.2 | Helped |
| combine local and nonlocal feature learning instead of using only PL (ablation) | PointASNL · ScanNet validation | mIoU: 56.1 -> 60.8 | Helped |
| add AS to PL+PNL (ablation) | PointASNL · ScanNet validation | mIoU: 60.8 -> 63.5 | Helped |
| add AS to PL+PNL (ablation) | PointASNL · ModelNet40 | overall accuracy: 93.2 -> 93.2 | No clear effect |
| add PNL to PointNet++ (ablation) | PointNet++ · ScanNet validation | mIoU: 48.9 -> 54.6 | Helped |
| add AS to PointNet+++PNL (ablation) | PointNet++ · ModelNet40 | overall accuracy: 93.0 -> 92.8 | Hurt |
| add AS to PointNet+++PNL (ablation) | PointNet++ · ScanNet validation | mIoU: 54.6 -> 55.4 | Helped |
| add PNL to DGCNN (ablation) | DGCNN · ScanNet validation | mIoU: 52.7 -> 56.7 | Helped |
| add AS to DGCNN+PNL (ablation) | DGCNN · ScanNet validation | mIoU: 56.7 -> 58.3 | Helped |
| replace random initial sampling with FPS (ablation) | adaptive sampling · ModelNet40 | overall accuracy: 87.9 -> 91.5 | Helped |
| use group-feature weighting rather than averaging neighbors (ablation) | adaptive sampling with FPS initialization · ModelNet40 | overall accuracy: 91.5 -> 93.2 | Helped |
| add repulsion loss (ablation) | PointASNL · semantic segmentation | performance | No clear effect |
Closest papers by meaning
- Point Cloud Upsampling Using Conditional Diffusion Module with Adaptive Noise Suppression (CVPR 2025 · similarity 0.88)
- PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2025 · similarity 0.87)
- LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes (CVPR 2024 · similarity 0.86)
- PointCVaR: Risk-Optimized Outlier Removal for Robust 3D Point Cloud Classification (AAAI 2024 · similarity 0.86)
- GCD-Sampling: A General Cross-scale Decoupled Sampling for Point Cloud (AAAI 2025 · similarity 0.86)
- You Should Learn to Stop Denoising on Point Clouds in Advance (AAAI 2025 · similarity 0.86)
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.