Research map / Point clouds / Shape and surface completion
Point Cloud Upsampling via Disentangled Refinement
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 disentangled refinement instead of the PU-GAN approach | Point cloud upsampling · ScanObjectNN, 4X | CD: 0.483 -> 0.315 | Helped |
| Use disentangled refinement instead of the PU-GAN approach | Point cloud upsampling · ScanObjectNN, 4X | HD: 5.323 -> 4.201 | Helped |
| Use disentangled refinement instead of the PU-GAN approach | Point cloud upsampling · ScanObjectNN, 4X | P2F: 5.053 -> 4.149 | Helped |
| Use disentangled refinement instead of the PU-GAN approach | Point cloud upsampling · ScanObjectNN, 16X | CD: 0.269 -> 0.199 | Helped |
| Use disentangled refinement instead of the PU-GAN approach | Point cloud upsampling · ScanObjectNN, 16X | HD: 7.127 -> 4.716 | Helped |
| Use disentangled refinement instead of the PU-GAN approach | Point cloud upsampling · ScanObjectNN, 16X | P2F: 6.306 -> 4.249 | Helped |
| Use the proposed method instead of PU-GAN | Synthetic point cloud upsampling · 16X, 0% noise | CD: 0.269 -> 0.199 | Helped |
| Use the proposed method instead of PU-GAN | Synthetic point cloud upsampling · 16X, 0.1% noise | CD: 0.309 -> 0.213 | Helped |
| Use the proposed method instead of PU-GAN | Synthetic point cloud upsampling · 16X, 0.5% noise | CD: 0.381 -> 0.229 | Helped |
| Use the proposed method instead of PU-GAN | Synthetic point cloud upsampling · 16X, 1.0% noise | CD: 0.562 -> 0.310 | Helped |
| Use the proposed method instead of PU-GAN | Synthetic point cloud upsampling · 16X, 2.0% noise | CD: 0.899 -> 0.592 | Helped |
| Add the spatial refiner to the dense generator (ablation) | Point cloud upsampling · Synthetic test data, 16X | CD: 0.684 -> 0.199 | Helped |
Closest papers by meaning
- Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning (AAAI 2024 · similarity 0.91)
- Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2024 · similarity 0.90)
- SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network (AAAI 2025 · similarity 0.90)
- PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2025 · similarity 0.89)
- SPU-PMD: Self-Supervised Point Cloud Upsampling via Progressive Mesh Deformation (CVPR 2024 · similarity 0.89)
- PointInfinity: Resolution-Invariant Point Diffusion Models (CVPR 2024 · 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.