arXiv Machine Learning
mmIR: Frequency-Space Inverse Rendering for 3D Millimeter-Wave Radar ADC Synthesis
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
Hugging Face Trending Papers
Sep 10
3D Point Splatting for mmWave Radar Novel View Synthesis
The paper introduces 3D Point Splatting (3DPS), a differentiable point renderer for millimeter-wave radar that directly implements the radar equation with an explicit material model and complex-valued outputs. Unlike prior methods, 3DPS simultaneously provides physical fidelity, complex-valued rendering, and multi-viewpoint tractability, enabling a single optimized scene to generate ADC, complex range profile, and range-azimuth images via FFT pipelines. On six outdoor ColoRadar scenes, 3DPS achieves a mean Pearson correlation of 0.587 on held-out range-azimuth images, outperforming optical-NVS baselines by 1.7x to 5.2x, and trains in about three minutes per scene on an RTX 4090.
arXiv Machine Learning
Sep 11
3D Point Splatting for mmWave Radar Novel View Synthesis
The paper introduces 3D Point Splatting (3DPS), a differentiable point renderer for millimeter‑wave radar that directly implements the radar equation with an explicit material model and complex‑valued outputs. Unlike previous methods, 3DPS preserves phase information and supports multiple output formats (ADC, CRP, RA) without retraining. On six outdoor ColoRadar scenes, it achieves a mean Pearson correlation of 0.587 on held‑out RA images, outperforming optical‑NVS baselines by 1.7× to 5.2× and trains in roughly three minutes per scene on a single RTX 4090.
arXiv Machine Learning
Sep 22
On Learning Spatial Structure from Pre-Beamforming Per-Antenna Range-Doppler Radar Measurements
This study explores whether spatial structure can be learned directly from pre-beamforming per-antenna range-Doppler (RD) radar measurements, bypassing traditional beamforming steps. Using a 6‑TX × 8‑RX automotive radar with a chirp‑sequence FMCW transmit scheme, the authors train a dual‑chirp shared‑weight encoder on raw RD tensors and evaluate spatial recoverability via bird’s‑eye‑view occupancy maps. Experiments across different transmit configurations (A‑only, B‑only, A+B) and receive apertures demonstrate that meaningful spatial structure is indeed recoverable through learned spatial mixing, without hand‑crafted signal‑processing stages.
arXiv Machine Learning
21h ago
4D Point Splatting for mmWave Radar Micro-Doppler Differentiable Rendering
arXiv:2611.08342v1 Announce Type: cross Abstract: Millimeter-wave radar resolves the micrometer displacements of a moving body as micro-Doppler, enabling gait, gesture, activity, pose and vital-sign...
arXiv Machine Learning
Jun 30
RadarTwin: Scene-Specific mmWave Radar Simulation and Learning for Mobile Indoor Perception
arXiv:2606. 28396v1 Announce Type: cross Abstract: 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.
arXiv Computer Vision
Oct 1
DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes
DyRAD introduces a novel radar novel‑view synthesis framework that models dynamic driving scenes by separating static background reflectors from motion‑tracked dynamic point reflectors, enabling the rendering of full range‑azimuth‑Doppler (RAD) tensors. The method derives reflector velocities from object tracks, projects them onto the line of sight, and uses a fixed analytic point‑spread function to avoid embedding sensor‑induced spread into the scene representation. This design allows accurate scene reconstruction and zero‑shot transfer to different radar configurations, achieving a 90.7% recovery of radar detections on the RADIal dataset compared to 26.9% for the best baseline.