AI Paper Atlas

Research map / 3D vision / Face and shape

MeshNet: Mesh Neural Network for 3D Shape Representation

AAAI 2019 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 338 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use MeshNet on mesh data instead of the strongest listed baseline, Kd-NetModelNet40 classification · ModelNet40Accuracy (%): 91.8 -> 91.9Helped
Use MeshNet instead of MVCNNModelNet40 retrieval · ModelNet40mAP (%): 79.5 -> 81.9Helped
Add the spatial descriptor and spatial feature (ablation)MeshNet · ModelNet40Accuracy (%): 83.5 -> 91.9Helped
Add the face rotate convolution to the spatial-only configuration (ablation)MeshNet · ModelNet40Accuracy (%): 88.2 -> 89.9Helped
Add face kernel correlation to the spatial-only configuration (ablation)MeshNet · ModelNet40Accuracy (%): 88.2 -> 87.0Hurt
Add mesh convolution to the configuration with both structural descriptors (ablation)MeshNet · ModelNet40Accuracy (%): 90.4 -> 91.9Helped
Replace concatenation aggregation with average pooling (ablation)MeshNet · ModelNet40Accuracy (%): 91.9 -> 90.7Hurt
Replace concatenation aggregation with max pooling (ablation)MeshNet · ModelNet40Accuracy (%): 91.9 -> 91.1Hurt

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