Research map / Point clouds / Shape and surface completion
Point Cloud Sampling via Graph Balancing and Gershgorin Disc Alignment
Chinthaka Dinesh, Gene Cheung, Ivan V. Bajić
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 |
|---|---|---|---|
| use proposed sub-sampling instead of AGBS | FGTV super-resolution · FGTV, ratio 0.2 | C2C error (x1e-2): 2.50 -> 2.21 | Improved |
| use proposed sub-sampling instead of AGBS | FGTV super-resolution · FGTV, ratio 0.6 | C2C error (x1e-2): 1.16 -> 1.03 | Improved |
| use proposed sub-sampling instead of second-best method | FGTV super-resolution · FGTV, ratios 0.2-0.6 | C2C error: 11.6%, 7.2%, 9.5%, 10.4%, 11.2% | Improved |
| use proposed sub-sampling instead of second-best method | FGTV super-resolution · FGTV, ratios 0.2-0.6 | C2P error: 17.5%, 12.1%, 12.9%, 7.5%, 8.3% | Improved |
| use proposed sub-sampling instead of AGBS | FGTV super-resolution · FGTV, ratio 0.2 | C2P error (x1e-3): 2.40 -> 1.98 | Improved |
| use proposed sub-sampling instead of AGBS | GTV super-resolution · GTV, ratio 0.2 | C2C error (x1e-2): 2.58 -> 2.29 | Improved |
| use proposed sub-sampling instead of AGBS | APSS super-resolution · APSS, ratio 0.2 | C2C error (x1e-2): 2.75 -> 2.48 | Improved |
| use proposed graph balancing instead of AGBS | sub-sampling · ratio 20% | lambda_min(B) (x1e-3): 1.92 -> 3.15 | Improved |
| use proposed graph balancing instead of AGBS | sub-sampling · ratio 60% | lambda_min(B) (x1e-3): 26.8 -> 38.4 | Improved |
| use proposed graph balancing instead of AGBS | balanced graph · Bunny | relative error: 0.357 -> 0.302 | Improved |
| use proposed graph balancing instead of AGBS | balanced graph · Bunny | DCS: 0.618 -> 0.670 | Improved |
| use proposed graph balancing instead of AGBS | balanced graph · Lucy | relative error: 0.503 -> 0.434 | Improved |
Closest papers by meaning
- GCD-Sampling: A General Cross-scale Decoupled Sampling for Point Cloud (AAAI 2025 · similarity 0.88)
- SAMBLE: Shape-Specific Point Cloud Sampling for an Optimal Trade-Off Between Local Detail and Global Uniformity (CVPR 2025 · similarity 0.88)
- EdgeMovingNet: Edge-preserving Point Cloud Reconstruction via Joint Geometry Features (CVPR 2025 · similarity 0.88)
- Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning (AAAI 2024 · similarity 0.88)
- Consistent Normal Orientation for 3D Point Clouds via Least Squares on Delaunay Graph (CVPR 2025 · similarity 0.87)
- LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image (NeurIPS 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.
