Research map / Point clouds / Shape and surface completion
Neural Points: Point Cloud Representation With Neural Fields for Arbitrary Upsampling
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 |
|---|---|---|---|
| represent each point with local neural fields and sample the resulting continuous surface | point cloud upsampling · Sketchfab 4× | CD (×10^-5): 2.26 -> 2.17 | Helped |
| represent each point with local neural fields and sample the resulting continuous surface | point cloud upsampling · PU-GAN 4× | CD (×10^-5): 11.18 -> 8.17 | Helped |
| represent each point with local neural fields and sample the resulting continuous surface | point cloud upsampling · Sketchfab 16× | CD (×10^-5): 0.80 -> 0.66 | Helped |
| represent each point with local neural fields and sample the resulting continuous surface | point cloud upsampling · PU-GAN 16× | CD (×10^-5): 3.51 -> 3.35 | Helped |
| use local KNN point sets rather than the whole-input point cloud for feature extraction (ablation) | Neural Points · Sketchfab 16× | CD (×10^-5): 2.49 -> 0.66 | Helped |
| add the normal loss L_nor (ablation) | Neural Points · Sketchfab 16× | CD (×10^-5): 0.70 -> 0.66 | Helped |
| add the integration loss L_int (ablation) | Neural Points · Sketchfab 16× | CD (×10^-5): 0.77 -> 0.66 | Helped |
| integrate local neural fields into a global surface (ablation) | Neural Points · Sketchfab 16× | CD (×10^-5): 0.83 -> 0.66 | Helped |
Closest papers by meaning
- Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation (CVPR 2022 · similarity 0.89)
- SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network (AAAI 2025 · similarity 0.88)
- Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning (AAAI 2024 · similarity 0.88)
- Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2024 · similarity 0.88)
- PU-Net: Point Cloud Upsampling Network (CVPR 2018 · similarity 0.88)
- NeuralIndicator: Implicit Surface Reconstruction from Neural Indicator Priors (ICML 2024 · similarity 0.86)
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.