AI Paper Atlas

Research map / Point clouds / Point cloud classification

Feature Extraction and Representation of Pre-training Point Cloud Based on Diffusion Models

Chang Qiu, Feipeng Da, Zilei Zhang

ICCV 2025 · 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 DXCA-Attention instead of MLP in CGNet (ablation)PreDifPoint · ScanObjectNN OBJ-BGoverall accuracy: 92.56 -> 93.42Improved
use bi-directional DXCA-Attention instead of one-way covariance attention (ablation)PreDifPoint · ScanObjectNN OBJ-BGoverall accuracy: 93.19 -> 93.42Improved
add density-adaptive time-step sampling instead of uniform sampling (ablation)PreDifPoint · ScanObjectNN OBJ-BGoverall accuracy: 93.31 -> 93.42Improved
use masking ratio 0.8 instead of no masking (ablation)PreDifPoint · ScanObjectNN OBJ-BGoverall accuracy: 91.58 -> 93.42Improved
use masking ratio 0.8 instead of 0.5 (ablation)PreDifPoint · ScanObjectNN OBJ-BGoverall accuracy: 90.96 -> 93.42Improved
use masking ratio 0.8 instead of 0.9 (ablation)PreDifPoint · ScanObjectNN OBJ-BGoverall accuracy: 92.34 -> 93.42Improved
use masking ratio 0.8 instead of 0.7 (ablation)PreDifPoint · ScanObjectNN OBJ-BGoverall accuracy: 91.85 -> 93.42Improved
use masking ratio 0.8 instead of no masking (ablation)PreDifPoint · S3DIS Area 5mIoU: 69.1 -> 71.8Improved
use masking ratio 0.8 instead of 0.9 (ablation)PreDifPoint · S3DIS Area 5mIoU: 70.6 -> 71.8Improved
use PreDifPoint diffusion pretraining instead of PointDifPreDifPoint · S3DIS Area 5mIoU: 70.0 -> 71.8Improved
use PreDifPoint instead of PointDifPreDifPoint · S3DIS Area 5mAcc: 77.1 -> 76.5Hurt
use PreDifPoint instead of PointDifPreDifPoint · ScanObjectNN PB-T50-RSoverall accuracy: 87.61 -> 87.96Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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