Research map / Point clouds / Shape and surface completion
Morphing and Sampling Network for Dense Point Cloud Completion
Read the paperCheck 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 the two-stage morphing, merging, and refining method instead of FCAE | ShapeNet point cloud completion · ShapeNet average | EMD×100: 8.32 -> 3.78 | Helped |
| Use the two-stage morphing, merging, and refining method instead of AtlasNet | ShapeNet point cloud completion · ShapeNet average | EMD×100: 6.53 -> 3.78 | Helped |
| Use the two-stage morphing, merging, and refining method instead of PCN | ShapeNet point cloud completion · ShapeNet average | EMD×100: 7.34 -> 3.78 | Helped |
| Add the expansion penalty to compact surface elements (ablation) | Morphing and Sampling Network · ShapeNet average | EMD×100: 3.91 -> 3.78 | Helped |
| Add the expansion penalty to compact surface elements (ablation) | Morphing and Sampling Network · ShapeNet average | CD×100: 1.20 -> 1.14 | Helped |
| Merge the coarse prediction with the input and refine the combination (ablation) | Morphing and Sampling Network · ShapeNet average | EMD×100: 4.08 -> 3.78 | Helped |
| Merge the coarse prediction with the input and refine the combination (ablation) | Morphing and Sampling Network · ShapeNet average | CD×100: 1.29 -> 1.14 | Helped |
| Use MDS rather than FPS to select the merged point subset (ablation) | Morphing and Sampling Network · ShapeNet average | EMD×100: 4.43 -> 3.78 | Helped |
| Use MDS rather than FPS to select the merged point subset (ablation) | Morphing and Sampling Network · ShapeNet average | CD×100: 1.11 -> 1.14 | Hurt |
| Add point-wise residual refining (ablation) | Morphing and Sampling Network · ShapeNet average | EMD×100: 3.89 -> 3.78 | Helped |
| Add point-wise residual refining (ablation) | Morphing and Sampling Network · ShapeNet average | CD×100: 1.21 -> 1.14 | Helped |
| Use EMD rather than CD as the training similarity metric (ablation) | Morphing and Sampling Network · ShapeNet average | EMD×100: 5.52 -> 3.78 | Helped |
Closest papers by meaning
- Digging into Intrinsic Contextual Information for High-fidelity 3D Point Cloud Completion (AAAI 2025 · similarity 0.91)
- ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors (ICLR 2025 · similarity 0.89)
- SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance (AAAI 2025 · similarity 0.89)
- Parametric Point Cloud Completion for Polygonal Surface Reconstruction (CVPR 2025 · similarity 0.88)
- A Computation-Aware Shape Loss Function for Point Cloud Completion (AAAI 2024 · similarity 0.88)
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (AAAI 2025 · similarity 0.88)
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.