Research map / 3D vision / Face and shape
Scan2Mesh: From Unstructured Range Scans to 3D Meshes
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 |
|---|---|---|---|
| Generate an explicit indexed mesh with Scan2Mesh instead of using the evaluated baselines | ShapeNet scan completion · ShapeNet test (8 classes) | Mesh distance: 0.0023 -> 0.0016 | Helped |
| Generate an explicit indexed mesh with Scan2Mesh instead of using the evaluated baselines | ShapeNet scan completion · ShapeNet test (8 classes) | Mesh normal similarity: 0.76 -> 0.83 | Helped |
| Use TSDF input instead of point-cloud input (ablation) | Scan2Mesh · ShapeNet test (8 classes), average | Mesh distance: 0.0019 -> 0.0016 | Helped |
| Use TSDF input instead of point-cloud input (ablation) | Scan2Mesh · ShapeNet test (8 classes), average | Mesh normal similarity: 0.80 -> 0.83 | Helped |
| Use one-to-one matching instead of greedy prediction-to-target association (ablation) | Scan2Mesh training · ShapeNet test (8 classes), average | Mesh distance: 0.0022 -> 0.0016 | Helped |
| Use one-to-one matching instead of greedy prediction-to-target association (ablation) | Scan2Mesh training · ShapeNet test (8 classes), average | Mesh normal similarity: 0.74 -> 0.83 | Helped |
| Predict faces on a dual graph of potential faces instead of predicting faces directly from vertices (ablation) | Scan2Mesh face prediction · ShapeNet test (8 classes), average | Mesh distance: 0.0042 -> 0.0016 | Helped |
| Predict faces on a dual graph of potential faces instead of predicting faces directly from vertices (ablation) | Scan2Mesh face prediction · ShapeNet test (8 classes), average | Mesh normal similarity: 0.66 -> 0.90 | Helped |
| Predict faces on a dual graph of potential faces instead of direct prediction with surface-near face targets (ablation) | Scan2Mesh face prediction · ShapeNet test (8 classes), average | Mesh distance: 0.0031 -> 0.0016 | Helped |
| Predict faces on a dual graph of potential faces instead of direct prediction with surface-near face targets (ablation) | Scan2Mesh face prediction · ShapeNet test (8 classes), average | Mesh normal similarity: 0.69 -> 0.90 | Helped |
Closest papers by meaning
- PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance (ICLR 2025 · similarity 0.88)
- Revisiting CAD Model Generation by Learning Raster Sketch (AAAI 2025 · similarity 0.87)
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.87)
- MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers (ICLR 2025 · similarity 0.87)
- MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers (CVPR 2024 · similarity 0.87)
- ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction (NeurIPS 2025 · 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.