Research map / Point clouds / Point cloud classification
GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model
Zixiang Ai, Zhenyu Cui, Yufei Guo, Wenwen Qiang, Lei Chen, Jiwen Lu, 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 Point Shift Prompter to linear probing (ablation) | Point-PQAE · ScanObjectNN PB_T50_RS | accuracy: 83.19 -> 86.55 | Improved |
| add Keypoint Prompter to linear probing (ablation) | Point-PQAE · ScanObjectNN PB_T50_RS | accuracy: 83.19 -> 85.83 | Improved |
| add Prompt Propagation to linear probing (ablation) | Point-PQAE · ScanObjectNN PB_T50_RS | accuracy: 83.19 -> 87.96 | Improved |
| add Prompt Propagation to linear probing (ablation) | Point-PQAE · uCO3D80 | accuracy: 63.78 -> 70.65 | Improved |
| add Prompt Propagation to Point Shift plus Keypoint prompters (ablation) | Point-PQAE · ScanObjectNN PB_T50_RS | accuracy: 88.62 -> 90.63 | Improved |
| add Prompt Propagation to Point Shift plus Keypoint prompters (ablation) | Point-PQAE · uCO3D80 | accuracy: 69.85 -> 74.53 | Improved |
| replace single-granular with multi-granular Point Shift Prompter (ablation) | GAPrompt++ · ScanObjectNN PB_T50_RS | accuracy: 85.72 -> 86.55 | Improved |
| replace single-granular with multi-granular Prompt Propagation (ablation) | GAPrompt++ · ScanObjectNN PB_T50_RS | accuracy: 86.53 -> 87.96 | Improved |
| replace point prompt with Keypoint Prompter (ablation) | GAPrompt++ · ScanObjectNN PB_T50_RS | accuracy: 84.91 -> 85.83 | Improved |
| full extension over conference GAPrompt (keypoint, multi-granular shift and propagation) (ablation) | GAPrompt · uCO3D80 | accuracy: 73.95 -> 74.53 | Improved |
| apply GAPrompt++ prompting to CLIP text encoder instead of full fine-tuning | CLIP-Lang · uCO3D80 | accuracy: 68.50 -> 77.54 | Improved |
| apply GAPrompt++ prompting to DINOv3 instead of full fine-tuning | DINOv3 · uCO3D80 | accuracy: 68.42 -> 71.95 | Improved |
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.
- GAPrompt — GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model (ICML 2025) · better on 5 of 5 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 0.96)
- On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation (NeurIPS 2025 · similarity 0.91)
- Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models (AAAI 2024 · similarity 0.90)
- Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis (NeurIPS 2024 · similarity 0.89)
- PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter (CVPR 2025 · similarity 0.89)
- Exploring Vision Semantic Prompt for Efficient Point Cloud Understanding (ICML 2025 · 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.
