# RadarTwin: Scene-Specific mmWave Radar Simulation and Learning for Mobile Indoor Perception

arXiv: https://arxiv.org/abs/2606.28396 · HTML: https://mlsanity.com/paper/2606.28396/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 26 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Builds on (most cited first, 6 of 6)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Material Recognition in the Wild with the Materials in Context Database](https://mlsanity.com/paper/1412.0623/) (2014)
- [RF-Diffusion: Radio Signal Generation via Time-Frequency Diffusion](https://mlsanity.com/paper/2404.09140/) (2024)
- [See Through Smoke: Robust Indoor Mapping with Low-cost mmWave Radar](https://mlsanity.com/paper/1911.00398/) (2019)
- [Radarize: Enhancing Radar SLAM with Generalizable Doppler-Based Odometry](https://mlsanity.com/paper/2311.11260/) (2023)

## Built on by (most cited first, 1 of 1)

- [KODAMA: Multimodal Digital Twin Reconstruction for Urban RF Propagation Modelling](https://mlsanity.com/paper/2609.07298/) (2026)

## Abstract (arXiv)

Millimeter-wave (mmWave) radar perception is limited by data scarcity: models trained on existing radar datasets fail to generalize to new objects, environments, and sensing trajectories. We present RadarTwin, a framework for generating deployment-specific radar training data before real data collection. Given a 3D reconstruction of a target space (phone LiDAR, robot-mounted sensing, or RGB-to-3D), RadarTwin uses a vision-language model to infer radar-relevant surface materials and a physics-based ray tracer to synthesize raw frequency-modulated continuous-wave (FMCW) radar measurements with multi-bounce propagation. To study what transfers from simulation to reality, we collect a paired real-simulated dataset spanning household objects, material classes, distances, rotations, translations, and mobile sensing trajectories. We show that simulated and real radar share the same object-discriminative shape and material features, and that modeling the environment's multipath is essential to matching real measurements. A representation trained on simulation alone recognizes real objects at 2.5 times chance with no real radar labels, and a few labeled examples raise this to 95.3% on a 12-way recognition task. RadarTwin enables training radar perception for a new space before any real radar data is collected there.