Research map / 3D vision / Face and shape
Cross-Atlas Convolution for Parameterization Invariant Learning on Textured Mesh Surface
Check 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 |
|---|---|---|---|
| Add cross-atlas convolution and pooling (ablation) | MeshMNIST classifier with MLP, max pooling, and FC layers · MeshMNIST test | accuracy: 88.6% -> 96.5% | Helped |
| Use MLP, row-wise max pooling, and FC layers instead of standard FC layers (ablation) | MeshMNIST classifier · MeshMNIST test | accuracy: 30.8% -> 88.6% | Helped |
| Use MLP, row-wise max pooling, and FC layers instead of standard FC layers (ablation) | MNIST classifier · MNIST test | accuracy: 99.2% -> 96.8% | Hurt |
| Add testing-stage fusion across individual and overlapping mesh parts (ablation) | Cross-atlas convolution on Ruemonge2014 · Ruemonge2014 | class avg. IoU: 61.58% -> 67.15% | Helped |
| Add natural-image training to texture-map training (ablation) | Cross-atlas convolution on Ruemonge2014 · Ruemonge2014 | class avg. IoU: 67.15% -> 67.91% | Helped |
| Train on images rather than texture maps (ablation) | Cross-atlas convolution on Ruemonge2014 · Ruemonge2014 | class avg. IoU: 67.15% -> 64.84% | Hurt |
Closest papers by meaning
- TextureNet: Consistent Local Parametrizations for Learning From High-Resolution Signals on Meshes (CVPR 2019 · similarity 0.91)
- Flatten Anything: Unsupervised Neural Surface Parameterization (NeurIPS 2024 · similarity 0.88)
- Convolutional Generation of Textured 3D Meshes (NeurIPS 2020 · similarity 0.87)
- TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features (CVPR 2025 · similarity 0.85)
- Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering (CVPR 2024 · similarity 0.84)
- Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape (ICLR 2024 · similarity 0.84)
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.