AI Paper Atlas

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

ICCV 2025 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 1 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 Rectification Prompter to linear-probing base (ablation)UPP (Point-MAE) · Noisy ModelNet40 (ablation, Point-MAE)accuracy (%): 88.41 -> 89.91Improved
add Completion Prompter after Rectification Prompter (ablation)UPP (Point-MAE) · Noisy ModelNet40 (ablation, Point-MAE)accuracy (%): 89.91 -> 91.41Improved
add Shape-Aware Unit (ablation)UPP (Point-MAE) · Noisy ModelNet40 (ablation, Point-MAE)accuracy (%): 91.41 -> 92.95Improved
rectify first instead of concurrent prompting (ablation)UPP · Noisy ModelNet40 (prompting order, Point-MAE)accuracy (%): 90.76 -> 92.95Improved
rectify first instead of complete first (ablation)UPP · Noisy ModelNet40 (prompting order, Point-MAE)accuracy (%): 91.18 -> 92.95Improved
complete first instead of concurrent (ablation)UPP · Noisy ModelNet40 (prompting order, Point-MAE)accuracy (%): 90.76 -> 91.18Improved
UPP instead of full fine-tuningPoint-MAE · Noisy ModelNet40accuracy (%): 89.42 -> 92.95Improved
UPP instead of full fine-tuningReCon · Noisy ModelNet40accuracy (%): 89.67 -> 91.69Improved
UPP instead of full fine-tuningPoint-FEMAE · Noisy ModelNet40accuracy (%): 89.59 -> 91.94Improved
UPP instead of full fine-tuningReCon · Noisy ShapeNet55accuracy (%): 89.01 -> 89.68Improved
Point-PEFT instead of full fine-tuningPoint-FEMAE · Noisy ShapeNet55accuracy (%): 88.63 -> 85.16Hurt
DAPT instead of full fine-tuningPoint-FEMAE · Noisy ShapeNet55accuracy (%): 88.63 -> 83.45Hurt

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