Research map / Point clouds / Point cloud classification
PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learning
Xinxing Yu, Ajian Liu, Sunyuan Qiang, Hui Ma, Liying Yang, Yuzhong Wang, Zhi Rao, Yanyan Liang
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 SPD to baseline (ablation) | PointCSP baseline · S3DIS Area5 (ablation) | mIoU: 84.7 -> 86.8 | Improved |
| add CSP to baseline (ablation) | PointCSP baseline · S3DIS Area5 (ablation) | mIoU: 84.7 -> 87.8 | Improved |
| add SPD on top of CSP (ablation) | PointCSP · S3DIS Area5 (ablation) | mIoU: 87.8 -> 88.2 | Improved |
| add CSP and SPD together (ablation) | PointCSP baseline · S3DIS Area5 (ablation) | mIoU: 84.7 -> 88.2 | Improved |
| add CSP and SPD together (ablation) | PointCSP baseline · S3DIS Area5 (ablation) | OA: 96.8 -> 98.1 | Improved |
| apply SPD to CamPoint (ablation) | CamPoint · S3DIS Area5 | mIoU: 83.3 -> 85.3 | Improved |
| apply SPD to CamPoint (ablation) | CamPoint · S3DIS Area5 | OA: 96.0 -> 96.2 | Improved |
| vary fine-tuning batch size (ablation) | PointCSP · S3DIS | mIoU | No clear effect |
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.
- CamPoint — CamPoint: Boosting Point Cloud Segmentation with Virtual Camera (CVPR 2025) · better on 5 of 5 shared results
- Sonata — Sonata: Self-Supervised Learning of Reliable Point Representations (CVPR 2025) · better on 2 of 2 shared results
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
- CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding (CVPR 2022 · similarity 0.89)
- Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos (ICCV 2023 · similarity 0.88)
- Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning (ICCV 2025 · similarity 0.88)
- Sonata: Self-Supervised Learning of Reliable Point Representations (CVPR 2025 · similarity 0.88)
- Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange (CVPR 2024 · similarity 0.87)
- Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception (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.
