AI Paper Atlas

Research map / Point clouds / Point cloud classification

MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis

Yaqian Liang, Shanshan Zhao, Baosheng Yu, Jing Zhang, Fazhi He

ECCV 2022 · Point clouds › Point cloud classification · approach: Masked point autoencoders · 54 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 MAE pre-training on ShapeNetMesh Transformer · Manifold40 classificationaccuracy: 91.5 -> 92.5Improved
add MAE pre-training on ModelNet40Mesh Transformer · Manifold40 classificationaccuracy: 91.5 -> 91.7Improved
pre-train on larger ShapeNet instead of ModelNet40MeshMAE · Manifold40 classificationaccuracy: 91.7 -> 92.5Improved
add pre-trainingMesh Transformer · COSEG-aliens segmentationaccuracy: 97.6 -> 98.0Improved
add pre-training on ModelNet40Mesh Transformer · Human Body segmentationaccuracy: 90.1 -> 90.1No clear effect
add the Chamfer vertex loss to the MSE face-feature loss (weight 0.5) (ablation)MeshMAE · ModelNet40 fine-tuningaccuracy: 91.2 -> 91.7Improved
add the Chamfer vertex loss (weight 0.5) in linear probing (ablation)MeshMAE · ModelNet40 linear probingaccuracy: 89.8 -> 91.1Improved
add MSE face-feature loss to the Chamfer loss alone (ablation)MeshMAE · ModelNet40 fine-tuningaccuracy: 90.6 -> 91.7Improved
raise Chamfer loss weight from 0.5 to 2 (ablation)MeshMAE · ModelNet40 linear probingaccuracy: 91.1 -> 89.7Hurt
randomize the order of face features in a patch (ablation)MeshMAE · ModelNet40 fine-tuningaccuracy: 91.7 -> 91.6No clear effect
embed the patch center instead of using learnable positional parameters (ablation)MeshMAE · ModelNet40 linear probingaccuracy: 46.1 -> 89.7Improved
embed the patch center instead of reshaping 64 face centers (ablation)MeshMAE · ModelNet40 linear probingaccuracy: 77.5 -> 89.7Improved

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