AI Paper Atlas

Research map / Point clouds / Point cloud classification

Low-Rank Test-Time Training for Pre-Trained Point Cloud Models

Ouyangzi Ye, Feifei Shao, Kexin Li, Yawei Luo, Zikai Song, Ping Liu, Fengda Zhang, Hongwei Wang, Jun Xiao

CVPR 2026 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining

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 masked feature alignment (MFA) to joint training (ablation)LoTT-PC · ScanObjectNN-Caccuracy (%) source-only: 48.3 -> 52.0Improved
use low-rank modulation units instead of full fine-tuning (ablation)LoTT-PC · ScanObjectNN-Caccuracy (%) online: 51.0 -> 54.1Improved
online test-time training on top of source-only modelLoTT-PC · ScanObjectNN-Caccuracy (%): 52.0 -> 54.1Improved
increase augmentation batch size from 1 to 8 masked views (ablation)LoTT-PC online TTT · ScanObjectNN-Caccuracy (%): 54.1 -> 51.3Hurt
raise test-time masking ratio from 0.1 to 0.9 (ablation)LoTT-PC online TTT · ScanObjectNN-Caccuracy (%): 54.1 -> 49.1Hurt
raise test-time masking ratio from 0.1 to 0.5 (ablation)LoTT-PC online TTT · ScanObjectNN-Caccuracy (%): 54.1 -> 53.4Hurt
infer with masked view or ensembles instead of complete view (ablation)LoTT-PC · ScanObjectNN-Caccuracy (%): 54.1 -> 53.9 (masked), 53.8 (ensemble)No clear effect
replace decoder-based auxiliary objectives with decoder-free MFA plus LoRA unitsMATE-Online / SMART-PC-Online · ModelNet40-Caccuracy (%): 71.3 -> 75.5 (vs MATE-Online)Improved
LoTT-PC versus MATE-Online on synthetic ShapeNet-CLoTT-PC-Online · ShapeNet-Caccuracy (%): 67.4 vs 69.1Mixed

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