Research map / 3D vision / Face and shape
Learning to Generate Structured Meshes with In-Context: Toward Generalization in Mesh Generation
Jing Xiao, Xinhai Chen, Jiaming Peng, Jie Liu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use ICL-Mesh instead of geometry-specific MeshONet | structured mesh generation · Case-1 | Max included angle: 120.631 -> 119.896 | Improved |
| use ICL-Mesh instead of geometry-specific MeshONet | structured mesh generation · Case-2 | Min included angle: 81.002 -> 80.035 | Hurt |
| use ICL-Mesh instead of geometry-specific MeshONet | structured mesh generation · Case-3 | Equiangle skewness: 0.307 -> 0.309 | Hurt |
| add more in-context examples at inference (ablation) | ICL-Mesh · MSE vs number of examples (0-4) | MSE | Improved |
| provide zero or one example at inference (ablation) | ICL-Mesh · few-shot | MSE | No clear effect |
| change the order of in-context examples (ascending, descending, OOD ranges, random) (ablation) | ICL-Mesh · seven prompt groups A-G | MSE | No clear effect |
| generate at 10x10, 60x60, 120x120 resolution after training on 30x30 meshes | ICL-Mesh · refinement and coarsening | simulation error | Improved |
Closest papers by meaning
- AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction (NeurIPS 2025 · similarity 0.87)
- ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction (NeurIPS 2025 · similarity 0.86)
- Flatten Anything: Unsupervised Neural Surface Parameterization (NeurIPS 2024 · similarity 0.85)
- MeshXL: Neural Coordinate Field for Generative 3D Foundation Models (NeurIPS 2024 · similarity 0.85)
- MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers (CVPR 2024 · similarity 0.84)
- PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance (ICLR 2025 · 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.
