AI Paper Atlas

Research map / Point clouds / Point cloud classification

Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning

Xu Yan, Huiqun Wang, Chen Wang, Lei Ren, Di Huang

ECCV 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 recalibrated positional embedding (RPE) (ablation)Point-MAE baseline · ScanObjectNN PB-T50accuracy (%): 88.58 -> 89.41Improved
add gated positional interface (GPI) (ablation)Point-MAE baseline · ScanObjectNN PB-T50accuracy (%): 88.58 -> 89.31Improved
combine RPE and GPI (ablation)MPL-MAE · ScanObjectNN PB-T50accuracy (%): 88.58 -> 90.35Improved
add topology preservation loss L_topo (ablation)MPL-MAE · ScanObjectNN PB-T50accuracy (%): 89.31 -> 90.35Improved
use cosine instead of Euclidean distance in RPE (ablation)MPL-MAE · ScanObjectNN PB-T50accuracy (%): 89.27 -> 90.35Improved
use Gumbel-Softmax instead of Sigmoid gating in GPI (ablation)MPL-MAE · ScanObjectNN PB-T50accuracy (%): 89.03 -> 90.35Improved
apply MPL-MAE over Point-MAE with pre-training augmentation removed (ablation)MPL-MAE · ModelNet40 linear probeaccuracy (%): 89.5 -> 92.2 (w/o Aug); 90.6 -> 92.9 (w/ Aug)Improved
replace Point-MAE with MPL-MAE under Gaussian noiseMPL-MAE · ModelNet40 noise sigma 3.0accuracy (%): 75.6 -> 80.8Improved
replace PCP-MAE with MPL-MAE in full fine-tuningMPL-MAE · ModelNet40 w/ voteaccuracy (%): 94.2 -> 94.4 (Point-FEMAE 94.5 higher)Mixed
replace PCP-MAE with MPL-MAE for segmentationMPL-MAE · S3DISmIoU: 61.3 -> 61.1 (mAcc 71.0 -> 71.7)Mixed
use MPL-MAE pretrained encoder for registrationMPL-MAE · ModelNet40 registrationMSE(R): 0.583 -> 0.335 (vs Point-MAE)Improved

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