Research map / Point clouds / Point cloud classification
TPC: Transformation-Specific Smoothing for Point Cloud Models
Wenda Chu, Linyi Li, Bo Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 TPC transformation-specific smoothing and certification instead of DeepG3D | PointNet-64 · ModelNet40 test; ZYX-rotation ±2° | certified accuracy (%): 61.6 -> 81.4 | Improved |
| Use TPC transformation-specific smoothing and certification instead of DeepG3D | PointNet-64 · ModelNet40 test; ZYX-rotation ±5° | certified accuracy (%): 49.6 -> 69.2 | Improved |
| Use TPC general-rotation certification | PointNet-64 · ModelNet40 test; general rotation ±10° | certified accuracy (%) | Improved |
| Use TPC transformation-specific smoothing and certification instead of DeepG3D | PointNet-64 · ModelNet40 test; Z-rotation ±20° | certified accuracy (%): 81.8 -> 84.2 | Improved |
| Use TPC transformation-specific smoothing and certification instead of DeepG3D | PointNet-64 · ModelNet40 test; Z-shear radius 0.03 | certified accuracy (%): 59.8 -> 83.4 | Improved |
| Use TPC transformation-specific smoothing and certification instead of DeepG3D | PointNet-64 · ModelNet40 test; Z-twist ±20° | certified accuracy (%): 20.3 -> 83.8 | Improved |
| Use TPC transformation-specific smoothing and certification instead of DeepG3D | PointNet-64 · ModelNet40 test; Z-taper radius 0.2 | certified accuracy (%): 23.9 -> 76.5 | Improved |
| Use TPC certification for composed transformations | PointNet-64 · ModelNet40 test; Z-twist ∘ Z-rotation ±20°, ±1° | certified accuracy (%): 13.8 -> 78.9 | Improved |
| Use TPC certification for composed transformations | PointNet-64 · ModelNet40 test; Z-taper ∘ Z-rotation radius 0.2, ±1° | certified accuracy (%): 17.5 -> 72.9 | Improved |
| Use TPC certification for composed transformations | PointNet-64 · ModelNet40 test; Z-twist ∘ Z-taper ∘ Z-rotation ±20°, radius 0.2, ±1° | certified accuracy (%): 4.6 -> 63.1 | Improved |
Closest papers by meaning
- CausalPC: Improving the Robustness of Point Cloud Classification by Causal Effect Identification (CVPR 2024 · similarity 0.86)
- SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds (ICML 2025 · similarity 0.85)
- PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion (NeurIPS 2025 · similarity 0.85)
- PointCVaR: Risk-Optimized Outlier Removal for Robust 3D Point Cloud Classification (AAAI 2024 · similarity 0.85)
- ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restoration (ICLR 2025 · similarity 0.85)
- Where Precision Meets Efficiency: Transformation Diffusion Model for Point Cloud Registration (AAAI 2025 · similarity 0.85)
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.
