Research map / Point clouds / Point cloud classification
GAM: Gradient Attention Module of Optimization for Point Clouds Analysis
Read the paperCheck 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 GAM | Point Trans. · S3DIS | mIoU: 73.5 -> 73.9 | Helped |
| Add GAM | Point Trans. · S3DIS | OA: 90.2 -> 89.9 | Hurt |
| Add GAM | PointMLP · ScanObjectNN PB_T50_RS | OA: 85.7 -> 86.1 | Helped |
| Add GAM | IA-SSD · KITTI validation | mIoU cars: 79.57 -> 79.16 | Hurt |
| Add GAM | IA-SSD · KITTI validation | mIoU pedestrians: 58.91 -> 59.31 | Helped |
| Add GAM | IA-SSD · KITTI validation | mIoU cyclists: 71.24 -> 72.58 | Helped |
| Add GAM | PointMLP* · ModelNet40 | OA: 94.5 -> 94.7 | Helped |
| Add GAM | CurveNet* · ShapeNet | Ins. mIoU: 86.8 -> 87.0 | Helped |
| Use distance information without gradient information (ablation) | PointNet++ · ScanObjectNN | OA: 86.2 -> 86.1 | Hurt |
| Use gradient information without distance information (ablation) | PointNet++ · ScanObjectNN | OA: 86.2 -> 86.5 | Helped |
| Use both distance and gradient information (ablation) | PointNet++ · ScanObjectNN | OA: 86.2 -> 87.0 | Helped |
| Use distance information without gradient information (ablation) | PointMLP · ScanObjectNN | OA: 85.7 -> 84.3 | Hurt |
Closest papers by meaning
- A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM) (ICML 2024 · similarity 0.86)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · similarity 0.85)
- DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis (CVPR 2025 · similarity 0.85)
- X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition (CVPR 2024 · similarity 0.84)
- On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation (NeurIPS 2025 · similarity 0.84)
- Mitigating Ambiguities in 3D Classification with Gaussian Splatting (CVPR 2025 · 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.