AI Paper Atlas

Research map / Point clouds / Point cloud classification

Reliable-View 2D-3D Key-Part Aligned Transformer with Reinforced Masking for 3D Point Cloud Understanding

Xianglong Jin, Zheng Wang, Rong Wang, Feiping Nie

AAAI 2026 · Point clouds › Point cloud classification · approach: Masked point autoencoders · 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 multi-view 2D input with KAT (ablation)Point-MAE baseline · ScanObjectNN OBJ-BGaccuracy (%): 92.94 -> 93.46Improved
add Reliable Multi-View Selector (RVS) (ablation)KAT with 3 views · ScanObjectNN OBJ-BGaccuracy (%): 93.46 -> 93.98Improved
add Reinforced Masking (RM) (ablation)KAT+RVS · ScanObjectNN OBJ-BGaccuracy (%): 93.98 -> 94.45Improved
select 3 views instead of 1 (ablation)KR-MAE · ScanObjectNN OBJ-BGaccuracy (%): 93.98 -> 94.45Improved
select 6 views instead of 3 (ablation)KR-MAE · ScanObjectNN OBJ-BGaccuracy (%): 94.45 -> 94.15Hurt
select 9 views instead of 3 (ablation)KR-MAE · ScanObjectNN OBJ-BGaccuracy (%): 94.45 -> 93.98Hurt
use aligned attention instead of MLP fusion (ablation)KR-MAE · ScanObjectNN OBJ-BGaccuracy (%): 92.60 -> 94.45Improved
use aligned attention instead of self-attention (ablation)KR-MAE · ScanObjectNN OBJ-BGaccuracy (%): 93.12 -> 94.45Improved
use aligned attention instead of standard cross-attention (ablation)KR-MAE · ScanObjectNN OBJ-BGaccuracy (%): 94.15 -> 94.45Improved
use reinforced masking instead of random masking, ratio 0.5 (ablation)Point cloud MAE pre-training · ShapeNet pre-training lossloss: 0.869 -> 0.790Improved
use reinforced masking instead of random masking, ratio 0.9 (ablation)Point cloud MAE pre-training · ShapeNet pre-training lossloss: 0.889 -> 0.866Improved
KR-MAE vs Point-MAE on few-shot 10-way 20-shotKR-MAE · ModelNet40 10-way 20-shotaccuracy (%): 95.0 -> 95.2Improved

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