Research map / Point clouds / Shape and surface completion
UPP: Unified Point-Level Prompting for Robust Point Cloud Analysis
Zixiang Ai, Zhenyu Cui, Yuxin Peng, Jiahuan Zhou
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 Rectification Prompter to linear-probing base (ablation) | UPP (Point-MAE) · Noisy ModelNet40 (ablation, Point-MAE) | accuracy (%): 88.41 -> 89.91 | Improved |
| add Completion Prompter after Rectification Prompter (ablation) | UPP (Point-MAE) · Noisy ModelNet40 (ablation, Point-MAE) | accuracy (%): 89.91 -> 91.41 | Improved |
| add Shape-Aware Unit (ablation) | UPP (Point-MAE) · Noisy ModelNet40 (ablation, Point-MAE) | accuracy (%): 91.41 -> 92.95 | Improved |
| rectify first instead of concurrent prompting (ablation) | UPP · Noisy ModelNet40 (prompting order, Point-MAE) | accuracy (%): 90.76 -> 92.95 | Improved |
| rectify first instead of complete first (ablation) | UPP · Noisy ModelNet40 (prompting order, Point-MAE) | accuracy (%): 91.18 -> 92.95 | Improved |
| complete first instead of concurrent (ablation) | UPP · Noisy ModelNet40 (prompting order, Point-MAE) | accuracy (%): 90.76 -> 91.18 | Improved |
| UPP instead of full fine-tuning | Point-MAE · Noisy ModelNet40 | accuracy (%): 89.42 -> 92.95 | Improved |
| UPP instead of full fine-tuning | ReCon · Noisy ModelNet40 | accuracy (%): 89.67 -> 91.69 | Improved |
| UPP instead of full fine-tuning | Point-FEMAE · Noisy ModelNet40 | accuracy (%): 89.59 -> 91.94 | Improved |
| UPP instead of full fine-tuning | ReCon · Noisy ShapeNet55 | accuracy (%): 89.01 -> 89.68 | Improved |
| Point-PEFT instead of full fine-tuning | Point-FEMAE · Noisy ShapeNet55 | accuracy (%): 88.63 -> 85.16 | Hurt |
| DAPT instead of full fine-tuning | Point-FEMAE · Noisy ShapeNet55 | accuracy (%): 88.63 -> 83.45 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Point-PEFT — Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models (AAAI 2024) · better on 7 of 7 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
- GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model (ICML 2025 · similarity 0.90)
- PointCVaR: Risk-Optimized Outlier Removal for Robust 3D Point Cloud Classification (AAAI 2024 · similarity 0.89)
- PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2025 · similarity 0.88)
- MICAS: Multi-grained In-Context Adaptive Sampling for 3D Point Cloud Processing (CVPR 2025 · similarity 0.88)
- Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis (NeurIPS 2024 · similarity 0.88)
- Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2024 · similarity 0.88)
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.
