Research map / Point clouds / Point cloud classification
PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing
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 |
|---|---|---|---|
| add the AFA module with densely connected local point features (ablation) | PointNet++ / PointWeb · S3DIS Area 5 | mIoU: 55.88 -> 60.28 | Helped |
| add the AFA module with densely connected local point features (ablation) | PointNet++ / PointWeb · S3DIS Area 5 | mAcc: 62.30 -> 66.64 | Helped |
| add the AFA module with densely connected local point features (ablation) | PointNet++ / PointWeb · S3DIS Area 5 | OA: 85.29 -> 86.97 | Helped |
| use feature subtraction rather than no combination, summation, or concatenation for paired features (ablation) | PointWeb impact function · S3DIS Area 5 | mIoU: 55.12 / 53.07 / 58.65 -> 60.28 | Helped |
| apply Softmax to impact coefficients (ablation) | PointWeb · S3DIS Area 5 | mIoU: 60.28 -> 59.11 | Hurt |
| share impact weights across channels (ablation) | PointWeb · S3DIS Area 5 | mIoU: 60.28 -> 58.27 | Hurt |
| apply impact factors directly to features rather than to feature differences (ablation) | PointWeb relation function · S3DIS Area 5 | mIoU: 59.79 -> 60.28 | Hurt |
| replace PointWeb's adaptive impact mechanism with GANN-style attention (ablation) | PointWeb · S3DIS Area 5 | mIoU: 58.23 -> 60.28 | Hurt |
Closest papers by meaning
- Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations (NeurIPS 2019 · similarity 0.88)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · similarity 0.87)
- Graph Smoothing for Enhanced Local Geometry Learning in Point Cloud Analysis (AAAI 2026 · similarity 0.87)
- Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentation (AAAI 2025 · similarity 0.86)
- Construct to Associate: Cooperative Context Learning for Domain Adaptive Point Cloud Segmentation (CVPR 2024 · similarity 0.85)
- Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange (CVPR 2024 · similarity 0.84)
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.