AI Paper Atlas

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

TPAMI 2026 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 3 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 Point Shift Prompter to linear probing (ablation)Point-PQAE · ScanObjectNN PB_T50_RSaccuracy: 83.19 -> 86.55Improved
add Keypoint Prompter to linear probing (ablation)Point-PQAE · ScanObjectNN PB_T50_RSaccuracy: 83.19 -> 85.83Improved
add Prompt Propagation to linear probing (ablation)Point-PQAE · ScanObjectNN PB_T50_RSaccuracy: 83.19 -> 87.96Improved
add Prompt Propagation to linear probing (ablation)Point-PQAE · uCO3D80accuracy: 63.78 -> 70.65Improved
add Prompt Propagation to Point Shift plus Keypoint prompters (ablation)Point-PQAE · ScanObjectNN PB_T50_RSaccuracy: 88.62 -> 90.63Improved
add Prompt Propagation to Point Shift plus Keypoint prompters (ablation)Point-PQAE · uCO3D80accuracy: 69.85 -> 74.53Improved
replace single-granular with multi-granular Point Shift Prompter (ablation)GAPrompt++ · ScanObjectNN PB_T50_RSaccuracy: 85.72 -> 86.55Improved
replace single-granular with multi-granular Prompt Propagation (ablation)GAPrompt++ · ScanObjectNN PB_T50_RSaccuracy: 86.53 -> 87.96Improved
replace point prompt with Keypoint Prompter (ablation)GAPrompt++ · ScanObjectNN PB_T50_RSaccuracy: 84.91 -> 85.83Improved
full extension over conference GAPrompt (keypoint, multi-granular shift and propagation) (ablation)GAPrompt · uCO3D80accuracy: 73.95 -> 74.53Improved
apply GAPrompt++ prompting to CLIP text encoder instead of full fine-tuningCLIP-Lang · uCO3D80accuracy: 68.50 -> 77.54Improved
apply GAPrompt++ prompting to DINOv3 instead of full fine-tuningDINOv3 · uCO3D80accuracy: 68.42 -> 71.95Improved

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.

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

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