Research map / 3D vision / Face and shape
Wave-Former: Through-Occlusion 3D Reconstruction via Wireless Shape Completion
Laura Dodds, Maisy Lam, Waleed Akbar, Yibo Cheng, Fadel Adib
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 specularity-aware inductive bias and reflection-dependent visibility (ablation) | Wave-Former · MITO | average chamfer distance: 0.105 -> 0.069 | Improved |
| add specularity-aware inductive bias and reflection-dependent visibility (ablation) | Wave-Former · MITO | 75th percentile chamfer distance: 0.120 -> 0.072 | Improved |
| add joint refinement and completion (ablation) | Wave-Former · MITO | average chamfer distance: 0.115 -> 0.105 | Improved |
| add entropy-guided surface selection (ablation) | Wave-Former · MITO | 75th percentile chamfer distance: 0.145 -> 0.122 | Improved |
| add entropy-guided surface selection (ablation) | Wave-Former · MITO | average chamfer distance: 0.116 -> 0.115 | No clear effect |
| use Wave-Former instead of vanilla vision-based completion on mmNorm partials | Wave-Former · MITO | recall: 60% -> 72% | Improved |
| use physics-aware completion instead of best mmWave baseline | Wave-Former · MITO | recall: 54% -> 72% | Improved |
| use Wave-Former instead of best baseline | Wave-Former · MITO | chamfer distance: 0.18 -> 0.069 | Improved |
| move from line-of-sight to fully occluded | Wave-Former · MITO | F-score: 78% -> 73% | No clear effect |
| use Wave-Former on extreme-coverage objects vs best baseline | Wave-Former · MITO extreme coverage | chamfer distance: 0.325 -> 0.126 | Improved |
Closest papers by meaning
- M4Human: A Large-Scale Multimodal mmWave Radar Benchmark for Human Mesh Reconstruction (CVPR 2026 · similarity 0.84)
- RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion (NeurIPS 2025 · similarity 0.83)
- MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight Perception (NeurIPS 2026 · similarity 0.83)
- FSC: Few-point Shape Completion (CVPR 2024 · similarity 0.82)
- Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion (CVPR 2024 · similarity 0.82)
- GeRaF: Neural Geometry Reconstruction from Radio Frequency Signals (NeurIPS 2025 · similarity 0.82)
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.
