# Wave-Former: Through-Occlusion 3D Reconstruction via Wireless Shape Completion

arXiv: https://arxiv.org/abs/2511.14152 · HTML: https://mlsanity.com/paper/2511.14152/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 77 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Builds on (most cited first, 30 of 33)

- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [3D Shape Generation and Completion through Point-Voxel Diffusion](https://mlsanity.com/paper/2104.03670/) (2021)
- [PCN: Point Completion Network](https://mlsanity.com/paper/1808.00671/) (2018)
- [OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation](https://mlsanity.com/paper/2301.07525/) (2023)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [What Do Single-view 3D Reconstruction Networks Learn?](https://mlsanity.com/paper/1905.03678/) (2019)
- [Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias](https://mlsanity.com/paper/2101.07296/) (2021)
- [ShapeFormer: Transformer-based Shape Completion via Sparse Representation](https://mlsanity.com/paper/2201.10326/) (2022)
- [A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion](https://mlsanity.com/paper/2112.03530/) (2021)
- [SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer](https://mlsanity.com/paper/2207.10315/) (2022)
- [ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer](https://mlsanity.com/paper/2302.14435/) (2023)
- [Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer](https://mlsanity.com/paper/2202.09367/) (2022)
- [Point-Cloud Completion with Pretrained Text-to-image Diffusion Models](https://mlsanity.com/paper/2306.10533/) (2023)
- [See Through Smoke: Robust Indoor Mapping with Low-cost mmWave Radar](https://mlsanity.com/paper/1911.00398/) (2019)
- [High Resolution Point Clouds from mmWave Radar](https://mlsanity.com/paper/2206.09273/) (2022)
- [ImmFusion: Robust mmWave-RGB Fusion for 3D Human Body Reconstruction in All Weather Conditions](https://mlsanity.com/paper/2210.01346/) (2022)
- [SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization](https://mlsanity.com/paper/2503.14558/) (2025)
- [Towards Dense and Accurate Radar Perception Via Efficient Cross-Modal Diffusion Model](https://mlsanity.com/paper/2403.08460/) (2024)
- [Diffusion-Based Point Cloud Super-Resolution for mmWave Radar Data](https://mlsanity.com/paper/2404.06012/) (2024)
- [Steady-state Non-Line-of-Sight Imaging](https://mlsanity.com/paper/1811.09910/) (2018)
- [3DRIMR: 3D Reconstruction and Imaging via mmWave Radar based on Deep Learning](https://mlsanity.com/paper/2108.02858/) (2021)
- [PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors](https://mlsanity.com/paper/2411.19036/) (2024)
- [DREAM-PCD: Deep Reconstruction and Enhancement of mmWave Radar Pointcloud](https://mlsanity.com/paper/2309.15374/) (2023)
- [Enabling Visual Recognition at Radio Frequency](https://mlsanity.com/paper/2405.19516/) (2024)
- [R2P: A Deep Learning Model from mmWave Radar to Point Cloud](https://mlsanity.com/paper/2207.10690/) (2022)
- [MMBaT: A Multi-task Framework for mmWave-based Human Body Reconstruction and Translation Prediction](https://mlsanity.com/paper/2312.10346/) (2023)
- [mmDEAR: mmWave Point Cloud Density Enhancement for Accurate Human Body Reconstruction](https://mlsanity.com/paper/2503.02375/) (2025)
- [ESCAPE: Equivariant Shape Completion via Anchor Point Encoding](https://mlsanity.com/paper/2412.00952/) (2024)
- [MITO: A Millimeter-Wave Dataset and Simulator for Non-Line-of-Sight Perception](https://mlsanity.com/paper/2502.10259/) (2025)

## Abstract (arXiv)

We present Wave-Former, a novel method capable of high-accuracy 3D shape reconstruction for completely occluded, diverse, everyday objects. This capability can open new applications spanning robotics, augmented reality, and logistics. Our approach leverages millimeter-wave (mmWave) wireless signals, which can penetrate common occlusions and reflect off hidden objects. In contrast to past mmWave reconstruction methods, which suffer from limited coverage and high noise, Wave-Former introduces a physics-aware shape completion model capable of inferring full 3D geometry. At the heart of Wave-Former's design is a novel three-stage pipeline which bridges raw wireless signals with recent advancements in vision-based shape completion by incorporating physical properties of mmWave signals. The pipeline proposes candidate geometric surfaces, employs a transformer-based shape completion model designed specifically for mmWave signals, and finally performs entropy-guided surface selection. This enables Wave-Former to be trained using entirely synthetic point-clouds, while demonstrating impressive generalization to real-world data. In head-to-head comparisons with state-of-the-art baselines, Wave-Former raises recall from 54% to 72% while maintaining a high precision of 85%.