Research map / Point clouds / Point cloud classification
Learning Local Displacements for Point Cloud Completion
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 |
|---|---|---|---|
| add the transformer architecture using the proposed operators | Ours (direct) · Completion3D | L2-Chamfer: 8.35 -> 6.64 | Helped |
| add the transformer architecture using the proposed operators | Ours (direct) · PCN | L1-Chamfer: 8.47 -> 7.96 | Helped |
| add the transformer architecture using the proposed operators | Ours (direct) · MVP | F-Score@1%: 0.801 -> 0.816 | Helped |
| add the transformer architecture using the proposed operators | Ours (direct) · NYU semantic scene completion | Average IoU: 40.0 -> 42.4 | Helped |
| add order loss to encourage output points to proceed from observed to occluded regions (ablation) | Ours (direct) · Completion3D | L2-Chamfer: 8.47 -> 8.35 | Helped |
| add order loss to encourage output points to proceed from observed to occluded regions (ablation) | Ours (transformer) · Completion3D | L2-Chamfer: 6.74 -> 6.64 | Helped |
| add order loss to encourage output points to proceed from observed to occluded regions (ablation) | Ours (direct) · PCN | L1-Chamfer: 8.59 -> 8.47 | Helped |
| add order loss to encourage output points to proceed from observed to occluded regions (ablation) | Ours (transformer) · PCN | L1-Chamfer: 8.09 -> 7.96 | Helped |
| add order loss to encourage output points to proceed from observed to occluded regions (ablation) | Ours (direct) · MVP | F-Score@1%: 0.788 -> 0.801 | Mixed |
| add order loss to encourage output points to proceed from observed to occluded regions (ablation) | Ours (transformer) · MVP | F-Score@1%: 0.795 -> 0.816 | Helped |
| use an adaptive semantic-loss weight instead of gamma=1 (ablation) | Ours (direct) · NYU semantic scene completion | Average IoU: 37.2 -> 40.0 | Helped |
| use an adaptive semantic-loss weight instead of gamma=1 (ablation) | Ours (transformer) · NYU semantic scene completion | Average IoU: 38.9 -> 42.4 | Helped |
Closest papers by meaning
- Point-based Instance Completion with Scene Constraints (ICLR 2025 · similarity 0.90)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · similarity 0.89)
- DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions (CVPR 2024 · similarity 0.89)
- PointAttN: You Only Need Attention for Point Cloud Completion (AAAI 2024 · similarity 0.88)
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (AAAI 2025 · similarity 0.87)
- Point Transformer V3: Simpler Faster Stronger (CVPR 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.