Research map / Point clouds / Shape and surface completion
Point2Cyl: Reverse Engineering 3D Objects From Point Clouds to Extrusion Cylinders
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 |
|---|---|---|---|
| use Point2Cyl instead of direct parameter prediction | extrusion-cylinder reconstruction · Fusion Gallery | Fit Cyl: 1.4132 -> 0.0704 | Helped |
| use Point2Cyl instead of direct parameter prediction | extrusion-cylinder reconstruction · DeepCAD | Fit Cyl: 0.4947 -> 0.0758 | Helped |
| add sketch consistency loss (ablation) | Point2Cyl · Fusion Gallery | Fit Cyl: 0.0826 -> 0.0704 | Helped |
| add sketch consistency loss (ablation) | Point2Cyl · DeepCAD | Fit Cyl: 0.0783 -> 0.0758 | Helped |
| add sketch consistency loss (ablation) | Point2Cyl · Fusion Gallery | E.A. (°): 9.795 -> 8.137 | Helped |
| add sketch consistency loss (ablation) | Point2Cyl · DeepCAD | E.A. (°): 8.085 -> 7.923 | Helped |
| use learned normals and sketch consistency loss instead of jet-fitting normals and no sketch loss (ablation) | Point2Cyl · Fusion Gallery | Fit Cyl: 0.0828 -> 0.0704 | Helped |
| use learned normals and sketch consistency loss instead of jet-fitting normals and no sketch loss (ablation) | Point2Cyl · DeepCAD | Fit Cyl: 0.0856 -> 0.0758 | Helped |
| use Point2Cyl instead of conditional DeepCAD generation | CAD reconstruction · DeepCAD test subset | Fit Cyl: 0.0959 -> 0.0758 | Helped |
Closest papers by meaning
- MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Images (NeurIPS 2024 · similarity 0.91)
- Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds (CVPR 2024 · similarity 0.88)
- CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention (CVPR 2024 · similarity 0.87)
- EdgeMovingNet: Edge-preserving Point Cloud Reconstruction via Joint Geometry Features (CVPR 2025 · similarity 0.86)
- MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scans (NeurIPS 2025 · similarity 0.86)
- MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds (NeurIPS 2025 · similarity 0.85)
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.