Research map / Graph learning / GNN architectures
Primal-Dual Mesh Convolutional Neural Networks
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace MeshCNN edge-based convolution/pooling with primal-dual attention and task-driven face pooling | PD-MeshNet · SHREC | accuracy: 98.6 -> 99.7 (split 16); 91.0 -> 99.1 (split 10) | Helped |
| replace MeshCNN with PD-MeshNet | PD-MeshNet · Cube Engraving | accuracy: 92.16 -> 94.39 | Helped |
| replace MeshCNN with PD-MeshNet | PD-MeshNet · COSEG face-label accuracy | accuracy: up to 4.24 | Helped |
| replace MeshCNN with PD-MeshNet | PD-MeshNet · Human Body segmentation | accuracy | Helped |
| sum-based instead of average-based feature aggregation in pooling | PD-MeshNet pooling · mesh tasks | accuracy | Helped |
| choose different dual graph configuration | PD-MeshNet · mesh tasks | accuracy | No clear effect |
| make network deeper | PD-MeshNet · mesh tasks | accuracy | Hurt |
| use more aggressive pooling | PD-MeshNet · mesh tasks | accuracy | Hurt |
Closest papers by meaning
- DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes (CVPR 2020 · similarity 0.91)
- FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis (CVPR 2018 · similarity 0.90)
- Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs (CVPR 2017 · similarity 0.89)
- Geometrically Principled Connections in Graph Neural Networks (CVPR 2020 · similarity 0.88)
- SplineCNN: Fast Geometric Deep Learning With Continuous B-Spline Kernels (CVPR 2018 · similarity 0.88)
- MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers (CVPR 2024 · similarity 0.87)
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.