Research map / Point clouds / Shape and surface completion
PrintAnything: Learning Geometric Plan Map for 3D Printing G-code Generation from Unoriented Point Clouds
Sangmin Hong, Daniel Sungho Jung, Heewon Kim, Kyoung Mu Lee
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 |
|---|---|---|---|
| add multi-slice conditioning (ablation) | PrintAnything · Slice-100K | CD: 0.059 -> 0.047 | Improved |
| add multi-slice conditioning (ablation) | PrintAnything · Slice-100K | F1 3D: 0.702 -> 0.741 | Improved |
| add multi-slice conditioning (ablation) | PrintAnything · Slice-100K | F1 2D: 0.652 -> 0.677 | Improved |
| add region map R to occupancy map M (ablation) | PrintAnything · Slice-100K | CD: 0.052 -> 0.046 | Improved |
| add region map R to occupancy map M (ablation) | PrintAnything · Slice-100K | F1 3D: 0.709 -> 0.728 | Improved |
| add region map R to occupancy map M (ablation) | PrintAnything · Slice-100K | extrusion smoothness: 1.055 -> 1.059 | No clear effect |
| add flow map Q (ablation) | PrintAnything · Slice-100K | extrusion smoothness: 0.081 -> 0.035 | Improved |
| add flow map Q (ablation) | PrintAnything · Slice-100K | rho-CV: 1.059 -> 0.909 | Improved |
| add flow map Q (ablation) | PrintAnything · Slice-100K | CD: 0.046 -> 0.047 | Mixed |
| use G-plan map instead of mesh + slicer pipeline (Poisson) | PrintAnything · Slice-100K | CD: 0.088 -> 0.047 | Improved |
| use G-plan map instead of mesh + slicer pipeline (DWG) | PrintAnything · Slice-100K | F1 2D: 0.496 -> 0.677 | Improved |
| use learned infill recommender instead of fixed scale baseline | PrintAnything · Slice-100K infill policy | Combined: 0.837 -> 0.937 | Improved |
Closest papers by meaning
- Slice-100K: A Multimodal Dataset for Extrusion-based 3D Printing (NeurIPS 2024 · similarity 0.89)
- SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation (NeurIPS 2026 · similarity 0.83)
- MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds (NeurIPS 2025 · similarity 0.83)
- CraftsMan3D: High-fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner (CVPR 2025 · similarity 0.82)
- Efficient Part-level 3D Object Generation via Dual Volume Packing (NeurIPS 2025 · similarity 0.82)
- LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image (NeurIPS 2024 · similarity 0.82)
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.
