Research map / Point clouds / Shape and surface completion
AnchorFormer: Point Cloud Completion From Discriminative Nodes
Read the paperCheck 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 |
|---|---|---|---|
| replace a global feature with discriminative anchors (ablation) | AnchorFormer point cloud completion · PCN | CDL1: 7.33 -> 6.81 | Helped |
| replace folding with Style-based Folding (ablation) | Anchor-based completion model · PCN | CDL1: 6.81 -> 6.77 | Helped |
| use point morphing instead of Style-based Folding (ablation) | Anchor-based completion model · PCN | CDL1: 6.77 -> 6.68 | Helped |
| add the compactness constraint Lcpa (ablation) | AnchorFormer · PCN | CDL1: 6.68 -> 6.59 | Helped |
| use anchors and point morphing with compactness regularization | point cloud completion · PCN | CDL1: 6.74 -> 6.59 | Helped |
| use AnchorFormer rather than SeedFormer | point cloud completion · ShapeNet-55 | CDL2: 0.92 -> 0.76 | Helped |
| use AnchorFormer rather than SeedFormer | point cloud completion · ShapeNet-55 | F1: 0.472 -> 0.558 | Helped |
| use AnchorFormer rather than SeedFormer | point cloud completion · ShapeNet-34 seen categories | F1: 0.452 -> 0.564 | Helped |
| use AnchorFormer rather than SeedFormer | point cloud completion · ShapeNet-34 unseen categories | F1: 0.402 -> 0.535 | Helped |
| use AnchorFormer rather than PoinTr | point cloud completion · KITTI | MMD: 0.526 -> 0.458 | Helped |
Closest papers by meaning
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · similarity 0.90)
- PointAttN: You Only Need Attention for Point Cloud Completion (AAAI 2024 · similarity 0.89)
- PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors (CVPR 2025 · similarity 0.89)
- SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance (AAAI 2025 · similarity 0.88)
- Position-Aware Guided Point Cloud Completion with CLIP Model (AAAI 2025 · similarity 0.87)
- Orthogonal Dictionary Guided Shape Completion Network for Point Cloud (AAAI 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.