Research map / Point clouds / Point cloud classification
PointMC: Multi-view Consistent Encoding and Center-Global Feature Fusion for Point Clouds Understanding
Xinxing Yu, Ajian Liu, Sunyuan Qiang, Yuzhong Wang, Hui Ma, 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 MCLPE position encoding (ablation) | PointMC baseline · ScanObjectNN PB_T50_RS | OA: 91.1 -> 93.1 | Improved |
| add MCLPE position encoding (ablation) | PointMC baseline · S3DIS Area5 | mIoU: 82.4 -> 82.5 | No clear effect |
| add CGFF module (ablation) | PointMC baseline · ScanObjectNN PB_T50_RS | OA: 91.1 -> 92.4 | Improved |
| add CGFF module (ablation) | PointMC baseline · S3DIS Area5 | mIoU: 82.4 -> 82.8 | Improved |
| combine MCLPE and CGFF (ablation) | PointMC baseline · S3DIS Area5 | mIoU: 82.4 -> 83.6 | Improved |
| use visibility-based MCPE instead of building-blocks grid encoding (V2) (ablation) | PointMC · S3DIS Area5 | mIoU: 80.6 -> 83.6 | Improved |
| use MCPE instead of cutting-cake encoding (V1) (ablation) | PointMC · ScanObjectNN PB_T50_RS | OA: 92.3 -> 93.4 | Improved |
| plug MCLPE into PointMLP (ablation) | PointMLP · ScanObjectNN | OA: 85.4 -> 86.3 | Improved |
| plug MCLPE into CamPoint (ablation) | CamPoint · ScanObjectNN | OA: 92.1 -> 92.8 | Improved |
| supervised PointMC vs self-supervised pretrained methods | PointMC · ModelNet40 few-shot | mAcc: 5-way 10-shot 93.0 vs MaskPoint 95.0 | Mixed |
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 3 of 3 shared results
- Sonata — Sonata: Self-Supervised Learning of Reliable Point Representations (CVPR 2025) · 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
- Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding (CVPR 2024 · similarity 0.88)
- PointMamba: A Simple State Space Model for Point Cloud Analysis (NeurIPS 2024 · similarity 0.88)
- Point Cloud Mamba: Point Cloud Learning via State Space Model (AAAI 2025 · similarity 0.88)
- PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter (CVPR 2025 · similarity 0.88)
- Sonata: Self-Supervised Learning of Reliable Point Representations (CVPR 2025 · similarity 0.87)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · 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.
