AI Paper Atlas

Research map / Point clouds / Point cloud classification

Point Cloud Self-supervised Learning via 3D to Multi-view Masked Learner

Zhimin Chen, Xuewei Chen, Xiao Guo, Yingwei Li, Longlong Jing, Liang Yang, Bing Li

ICCV 2025 · Point clouds › Point cloud classification · approach: Masked point autoencoders · 13 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 token-level reconstruction (ablation)Multiview-ML (Point-MAE base) · ScanObjectNN PB-T50-RSaccuracy (%): 85.18 -> 87.07Improved
add instance-level intra/inter-modality prediction on top of token reconstruction (ablation)Multiview-ML · ScanObjectNN PB-T50-RSaccuracy (%): 87.07 -> 88.11Improved
add MSMH attention to token plus instance reconstruction (ablation)Multiview-ML · ScanObjectNN PB-T50-RSaccuracy (%): 88.11 -> 88.93Improved
feed only 3D input rather than 3D plus 2D input (ablation)Multiview-ML · ScanObjectNN PB-T50-RSaccuracy (%): 87.02 -> 88.93Improved
predict only 2D multi-view output instead of 3D and 2D (ablation)Multiview-ML · ScanObjectNN PB-T50-RSaccuracy (%): 88.93 -> 84.25Hurt
pretrain with Multiview-ML before 3DETR fine-tuning3DETR · ScanNetV2AP50: 37.9 -> 43.3Improved
add Multiview-ML pretraining to Point-M2AEPoint-M2AE · ModelNet40accuracy (%): +0.4%Improved
add 3D-to-multi-view projection and MSMH to I2P-MAE and ReConI2P-MAE, ReCon · ScanObjectNNaccuracyImproved

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