Research map / Point clouds / Shape and surface completion
Learning 3D Shape Completion From Laser Scan Data With Weak Supervision
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 |
|---|---|---|---|
| Amortize maximum-likelihood inference with a learned encoder | 3D shape completion · KITTI val | Completeness [m]: 0.131 (0.129) -> 0.091 | Helped |
| Use an AML encoder instead of per-instance ML optimization | 3D shape completion · SN-clean | runtime [s]: 30 -> 0.001 | Helped |
| Use an AML encoder instead of per-instance ML optimization | 3D shape completion · SN-clean | Completeness [vx]: 0.845 -> 0.877 | No clear effect |
| Use weak supervision rather than full shape supervision | 3D shape completion · KITTI val | Completeness [m]: 0.176 (0.174) -> 0.091 | Helped |
| Add weighting to the per-voxel free-space loss (ablation) | AML · KITTI val | Completeness [m]: 0.117 -> 0.091 | Helped |
| Use category-agnostic rather than category-specific AML models (ablation) | AML · ModelNet all categories | Hamming distance: 0.016 -> 0.065 | Mixed |
Closest papers by meaning
- 3D Shape Completion with Multi-View Consistent Inference (AAAI 2020 · similarity 0.90)
- ShapeFormer: Transformer-Based Shape Completion via Sparse Representation (CVPR 2022 · similarity 0.89)
- Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis (CVPR 2017 · similarity 0.89)
- FSC: Few-point Shape Completion (CVPR 2024 · similarity 0.89)
- Learning Generalizable Shape Completion with SIM(3) Equivariance (NeurIPS 2025 · similarity 0.87)
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (AAAI 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.