Research map / Point clouds / Shape and surface completion
HVPUNet: Hybrid-Voxel Point-cloud Upsampling Network
Juhyung Ha, Vibhas Kumar Vats, Soon-heung Jung, Alimoor Reza, David J. Crandall
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 |
|---|---|---|---|
| add operational voxel expansion (ablation) | HVPUNet · PU-GAN | Dice/IoU | Improved |
| add distance-based pruning (ablation) | HVPUNet · PU-GAN | Dice/IoU | Improved |
| raise expansion kernel threshold to 5 or above, optimal 7 (ablation) | HVPUNet · PU-GAN | Dice/IoU: 5 -> 7 | Improved |
| HVPUNet instead of RepKPU, inference speed | HVPUNet · PU-GAN | runtime (sec): 345.387 -> 1.543 | Improved |
| HVPUNet instead of RepKPU, memory | HVPUNet · PU-GAN | VRAM (GB): 33.621 -> 2.817 | Improved |
| HVPUNet instead of Grad-PU, Dice | HVPUNet · PU-GAN | Dice: 0.698 -> 0.707 | Improved |
| HVPUNet instead of Grad-PU, P2F average | HVPUNet · PU-GAN | P2F avg (x10^3): 2.143 -> 2.736 | Hurt |
| HVPUNet instead of RepKPU, P2F max | HVPUNet · PU-GAN | P2F max (x10^3): 46.822 -> 26.023 | Improved |
| HVPUNet under 512-point undersampled input instead of RepKPU | HVPUNet · PU-GAN | Dice: 0.550 -> 0.604 | Improved |
| HVPUNet instead of RepKPU on PU1K P2F max | HVPUNet · PU1K | P2F max (x10^3): 13.872 -> 25.438 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- RepKPU — RepKPU: Point Cloud Upsampling with Kernel Point Representation and Deformation (CVPR 2024) · better on 10 of 10 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning (AAAI 2024 · similarity 0.94)
- Point Cloud Upsampling via Disentangled Refinement (CVPR 2021 · similarity 0.90)
- SPU-PMD: Self-Supervised Point Cloud Upsampling via Progressive Mesh Deformation (CVPR 2024 · similarity 0.88)
- SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network (AAAI 2025 · similarity 0.88)
- Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2024 · similarity 0.87)
- EdgeMovingNet: Edge-preserving Point Cloud Reconstruction via Joint Geometry Features (CVPR 2025 · 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.
