Research map / Point clouds / Point cloud classification
Explore In-Context Learning for 3D Point Cloud Understanding
Zhongbin Fang, Xiangtai Li, Xia Li, Joachim M. Buhmann, Chen Change Loy, Mengyuan Liu
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 Joint Sampling to align input and target patch indices (ablation) | PIC-Cat · Denoising | Chamfer Distance (x1000): 29.3 -> 5.3 | Improved |
| Add Joint Sampling to align input and target patch indices (ablation) | PIC-Cat · Part segmentation | mIOU: 17.03 -> 78.95 | Improved |
| Use FPS instead of random sampling (ablation) | PIC-Sep · Reconstruction | Chamfer Distance (x1000): 42.6 -> 4.7 | Improved |
| Use FPS instead of random sampling (ablation) | PIC-Sep · Part segmentation | mIOU: 77.24 -> 74.95 | Hurt |
| Use L2 rather than L1 loss (ablation) | PIC-Sep · Reconstruction | Chamfer Distance (x1000): 5.0 -> 4.7 | Improved |
| Replace L2 loss with combined L1 and L2 loss (ablation) | PIC-Sep · Reconstruction | Chamfer Distance (x1000): 4.7 -> 5.3 | Hurt |
| Reduce mask ratio from 0.7 to 0.5 (ablation) | PIC-Sep · Reconstruction | Chamfer Distance (x1000): 4.7 -> 4.0 | Improved |
| Reduce mask ratio from 0.7 to 0.6 (ablation) | PIC-Sep · Registration | Chamfer Distance (x1000): 10.3 -> 9.4 | Improved |
| Use 0.7 mask ratio instead of 0.2 (ablation) | PIC-Sep · Denoising | Chamfer Distance (x1000): 33.5 -> 7.6 | Improved |
| Select prompts by Chamfer Distance rather than randomly (ablation) | PIC-Sep · Registration | Chamfer Distance (x1000): 10.3 -> 4.1 | Improved |
| Place the prompt before rather than after the query (ablation) | PIC-Sep · Reconstruction | Chamfer Distance (x1000): 4.8 -> 4.7 | No clear effect |
Closest papers by meaning
- Point-In-Context: Understanding Point Cloud via In-Context Learning (IJCV 2026 · similarity 0.93)
- Deformation-based In-Context Learning for Point Cloud Understanding (CVPR 2026 · similarity 0.90)
- Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis (CVPR 2025 · similarity 0.88)
- Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis (NeurIPS 2024 · similarity 0.88)
- MICAS: Multi-grained In-Context Adaptive Sampling for 3D Point Cloud Processing (CVPR 2025 · similarity 0.87)
- Sonata: Self-Supervised Learning of Reliable Point Representations (CVPR 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.
