Research map / Point clouds / Point cloud classification
PU-GCN: Point Cloud Upsampling Using Graph Convolutional Networks
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 PU-GCN instead of PU-GAN | point cloud upsampling · PU-GAN dataset | CD (10^-3): 0.280 -> 0.258 | Helped |
| Use PU-GCN instead of PU-GAN | point cloud upsampling · PU-GAN dataset | P2F (10^-3): 2.330 -> 2.721 | Hurt |
| Use PU-GCN instead of 3PU | point cloud upsampling · PU1K | CD (10^-3): 0.935 -> 0.585 | Helped |
| Add NodeShuffle to PU-Net in place of its original upsampler (ablation) | PU-Net · PU1K | CD (10^-3): 1.155 -> 0.974 | Helped |
| Add NodeShuffle to 3PU in place of its original upsampler (ablation) | 3PU · PU1K | CD (10^-3): 0.935 -> 0.780 | Helped |
| Use GCN-based NodeShuffle instead of MLPShuffle (ablation) | PU-GCN · PU1K | CD (10^-3): 0.682 -> 0.585 | Helped |
| Use Inception DenseGCN instead of DenseGCN alone (ablation) | PU-GCN · PU1K | CD (10^-3): 0.753 -> 0.585 | Helped |
| Use two DenseGCN blocks rather than one (ablation) | Inception DenseGCN · PU1K | CD (10^-3): 0.630 -> 0.585 | Helped |
| Add dilated graph convolutions (ablation) | Inception DenseGCN · PU1K | CD (10^-3): 0.624 -> 0.585 | Helped |
| Add residual connections (ablation) | Inception DenseGCN · PU1K | CD (10^-3): 0.621 -> 0.585 | Helped |
| Add global pooling (ablation) | Inception DenseGCN · PU1K | CD (10^-3): 0.663 -> 0.585 | Helped |
| Increase Inception DenseGCN blocks from one to two (ablation) | PU-GCN · PU1K | CD (10^-3): 0.639 -> 0.585 | Helped |
Closest papers by meaning
- SPU-IMR: Self-supervised Arbitrary-scale Point Cloud Upsampling via Iterative Mask-recovery Network (AAAI 2025 · similarity 0.87)
- DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning (AAAI 2024 · similarity 0.87)
- GCD-Sampling: A General Cross-scale Decoupled Sampling for Point Cloud (AAAI 2025 · similarity 0.87)
- Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling (AAAI 2024 · similarity 0.87)
- Point Cloud Upsampling Using Conditional Diffusion Module with Adaptive Noise Suppression (CVPR 2025 · similarity 0.87)
- RepKPU: Point Cloud Upsampling with Kernel Point Representation and Deformation (CVPR 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.