Research map / Point clouds / Point cloud classification
Feature Extraction and Representation of Pre-training Point Cloud Based on Diffusion Models
Chang Qiu, Feipeng Da, Zilei Zhang
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 |
|---|---|---|---|
| add DXCA-Attention instead of MLP in CGNet (ablation) | PreDifPoint · ScanObjectNN OBJ-BG | overall accuracy: 92.56 -> 93.42 | Improved |
| use bi-directional DXCA-Attention instead of one-way covariance attention (ablation) | PreDifPoint · ScanObjectNN OBJ-BG | overall accuracy: 93.19 -> 93.42 | Improved |
| add density-adaptive time-step sampling instead of uniform sampling (ablation) | PreDifPoint · ScanObjectNN OBJ-BG | overall accuracy: 93.31 -> 93.42 | Improved |
| use masking ratio 0.8 instead of no masking (ablation) | PreDifPoint · ScanObjectNN OBJ-BG | overall accuracy: 91.58 -> 93.42 | Improved |
| use masking ratio 0.8 instead of 0.5 (ablation) | PreDifPoint · ScanObjectNN OBJ-BG | overall accuracy: 90.96 -> 93.42 | Improved |
| use masking ratio 0.8 instead of 0.9 (ablation) | PreDifPoint · ScanObjectNN OBJ-BG | overall accuracy: 92.34 -> 93.42 | Improved |
| use masking ratio 0.8 instead of 0.7 (ablation) | PreDifPoint · ScanObjectNN OBJ-BG | overall accuracy: 91.85 -> 93.42 | Improved |
| use masking ratio 0.8 instead of no masking (ablation) | PreDifPoint · S3DIS Area 5 | mIoU: 69.1 -> 71.8 | Improved |
| use masking ratio 0.8 instead of 0.9 (ablation) | PreDifPoint · S3DIS Area 5 | mIoU: 70.6 -> 71.8 | Improved |
| use PreDifPoint diffusion pretraining instead of PointDif | PreDifPoint · S3DIS Area 5 | mIoU: 70.0 -> 71.8 | Improved |
| use PreDifPoint instead of PointDif | PreDifPoint · S3DIS Area 5 | mAcc: 77.1 -> 76.5 | Hurt |
| use PreDifPoint instead of PointDif | PreDifPoint · ScanObjectNN PB-T50-RS | overall accuracy: 87.61 -> 87.96 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Point-BERT — Point-BERT: Pre-Training 3D Point Cloud Transformers With Masked Point Modeling (CVPR 2022) · better on 2 of 2 shared results
- PointCNN — PointCNN: Convolution On X-Transformed Points (NeurIPS 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Point Cloud Pre-training with Diffusion Models (CVPR 2024 · similarity 0.95)
- Point Cloud Upsampling Using Conditional Diffusion Module with Adaptive Noise Suppression (CVPR 2025 · similarity 0.89)
- A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling (CVPR 2024 · similarity 0.88)
- TIGER: Time-Varying Denoising Model for 3D Point Cloud Generation with Diffusion Process (CVPR 2024 · similarity 0.88)
- Where Precision Meets Efficiency: Transformation Diffusion Model for Point Cloud Registration (AAAI 2025 · similarity 0.88)
- PointInfinity: Resolution-Invariant Point Diffusion Models (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.
