Research map / Point clouds / Shape and surface completion
Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation
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 self-supervised implicit surface projection for arbitrary-scale upsampling instead of supervised PU-DR | Point cloud upsampling · ShapeNet test, 2×–16× | F-score: 371 vs 409; 561 vs 625; 706 vs 708; 772 vs 779 | Mixed |
| Use self-supervised implicit surface projection for arbitrary-scale upsampling instead of supervised PU-DR | Point cloud upsampling · ShapeNet test, 2×–16× | CD: 12.1 vs 11.0; 10.1 vs 8.71; 8.70 vs 8.34; 7.65 vs 7.29 | Hurt |
| Use self-supervised implicit surface projection for arbitrary-scale upsampling instead of supervised PU-DR | Point cloud upsampling · ShapeNet test, 2×–16× | std: 10.2 vs 4.05; 9.35 vs 3.89; 8.84 vs 4.97; 8.34 vs 4.72 | Hurt |
| Use self-supervised implicit surface projection for arbitrary-scale upsampling instead of supervised Meta-PU | Point cloud upsampling · ShapeNet test, 4× | NUC at p=0.2%: 1.72 vs 2.50 | Helped |
| Set M=10 instead of M=3 in the seed-to-surface distance approximation (ablation) | SSAS · Cow, 4× | surface continuity | Helped |
| Set M=10 instead of M=3 in the seed-to-surface distance approximation (ablation) | SSAS · Cow, 4× | outliers | Hurt |
| Remove outlier removal (ablation) | SSAS · Cow, 4× | outlier presence | Hurt |
Closest papers by meaning
- SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network (AAAI 2025 · similarity 0.92)
- Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2024 · similarity 0.92)
- Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning (AAAI 2024 · similarity 0.89)
- SPU-PMD: Self-Supervised Point Cloud Upsampling via Progressive Mesh Deformation (CVPR 2024 · similarity 0.87)
- PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2025 · similarity 0.87)
- A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling (CVPR 2024 · 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.