AI Paper Atlas

Research map / Point clouds / Point cloud classification

Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis

Mengke Li, Lihao Chen, Peng Zhang, Yiu‐ming Cheung, Hui Fei Huang

TPAMI 2026 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add 2D pre-trained model (ViT-B) to point embedding baseline (ablation)Point-PN point embedding · ScanObjectNN PB-T50-RSaccuracy: 87.1 -> 90.1Improved
add 2D pre-trained model (ViT-B) to point embedding baseline (ablation)Point-PN point embedding · ModelNet40accuracy: 93.8 -> 93.9No clear effect
add position injection (PosIn) (ablation)PE + 2D · ScanObjectNN PB-T50-RSaccuracy: 90.1 -> 91.2Improved
add point-prompt tuning (PPT) (ablation)PE + 2D · ScanObjectNN PB-T50-RSaccuracy: 90.1 -> 91.4Improved
combine PosIn and PPT (ablation)PE + 2D · ScanObjectNN PB-T50-RSaccuracy: 91.4 -> 92.6Improved
combine PosIn and PPT (ablation)PE + 2D · ModelNet40accuracy: 93.9 -> 94.2Improved
use DeiT instead of ViT-B as 2D prior (ablation)APPT · ScanObjectNN PB-T50-RSaccuracy: 92.6 -> 88.9Hurt
use DINOv2 instead of ViT-B as 2D prior (ablation)APPT · ScanObjectNN PB-T50-RSaccuracy: 92.6 -> 92.6No clear effect
use RoBERTa text prior instead of CLIP text (ablation)APPT · ScanObjectNN PB-T50-RSaccuracy: 91.4 -> 87.3Hurt
use audio prior (ImageBind) instead of ViT-B (ablation)APPT · ScanObjectNN PB-T50-RSaccuracy: 92.6 -> 88.9Hurt
replace APF's weight setting with APPT shared-weights prompt generatorAPF · ScanObjectNN PB-T50-RSaccuracy: 87.8 -> 92.6Improved
APPT versus APF in 10-way 20-shotAPF · ModelNet40 10-way 20-shotaccuracy: 95.7 -> 95.3Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy