Learning Spatial Structure from Pre-Beamforming Per-Antenna Range-Doppler Radar Data via Visibility-Aware Cross-Modal Supervision

• URL: http://arxiv.org/abs/2604.01921v1
• Date: Thu, 02 Apr 2026 11:39:00 GMT
• Title: Learning Spatial Structure from Pre-Beamforming Per-Antenna Range-Doppler Radar Data via Visibility-Aware Cross-Modal Supervision
• Abstract summary: Can meaningful spatial structure be learned directly from pre-beamforming per-antenna range-Doppler measurements?<n>Experiments are conducted on a 6-TX x 8-RX (48 virtual antennas)<n>We operate on pre-beamforming per-antenna RD tensors using a dual-chirp shared-weight encoder trained in an end-to-end, fully data-driven manner.
• Score: 2.348805691644085
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automotive radar perception pipelines commonly construct angle-domain representations via beamforming before applying learning-based models. This work instead investigates a representational question: can meaningful spatial structure be learned directly from pre-beamforming per-antenna range-Doppler (RD) measurements? Experiments are conducted on a 6-TX x 8-RX (48 virtual antennas) commodity automotive radar employing an A/B chirp-sequence frequency-modulated continuous-wave (CS-FMCW) transmit scheme, in which the effective transmit aperture varies between chirps (single-TX vs. multi-TX), enabling controlled analysis of chirp-dependent transmit configurations. We operate on pre-beamforming per-antenna RD tensors using a dual-chirp shared-weight encoder trained in an end-to-end, fully data-driven manner, and evaluate spatial recoverability using bird's-eye-view (BEV) occupancy as a geometric probe rather than a performance-driven objective. Supervision is visibility-aware and cross-modal, derived from LiDAR with explicit modeling of the radar field-of-view and occlusion-aware LiDAR observability via ray-based visibility. Through chirp ablations (A-only, B-only, A+B), range-band analysis, and physics-aligned baselines, we assess how transmit configurations affect geometric recoverability. The results indicate that spatial structure can be learned directly from pre-beamforming per-antenna RD tensors without explicit angle-domain construction or hand-crafted signal-processing stages.

Related papers

• Learning Structurally Consistent Representations for Multi-View Radar Semantic Segmentation [2.4705928100051135]
  We introduce a unified higher-order structural alignment framework for multi-view radar segmentation.<n>The proposed method refines radar feature representations using learnable hypergraphs to capture higher-order dependencies.<n>Experiments on the CARRADA and RADIal benchmarks demonstrate consistent improvements over strong radar-specific baselines.
  arXiv  Detail & Related papers  (2026-06-30T12:57:15Z)
• OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation [100.36917520403227]
  We present a unified text-conditioned diffusion framework that generates LiDAR scans in a shared range-image representation across eight representative domains.<n>In the absence of a public consolidated benchmark, we construct an 8-domain dataset by combining real-world scans with physically based weather simulation and systematic beam reduction.
  arXiv  Detail & Related papers  (2026-05-13T17:42:20Z)
• RAVEN: Radar Adaptive Vision Encoders for Efficient Chirp-wise Object Detection and Segmentation [11.345174599707859]
  RAVEN is a computationally efficient deep learning architecture for FMCW radar perception.<n>Across automotive radar benchmarks, the approach reports strong object detection and BEV free-space segmentation performance.
  arXiv  Detail & Related papers  (2026-04-06T07:30:45Z)
• RLPR: Radar-to-LiDAR Place Recognition via Two-Stage Asymmetric Cross-Modal Alignment for Autonomous Driving [14.25906590501402]
  Radar-to-LiDAR place recognition can localize radar scans within existing LiDAR maps.<n>We propose RLPR, a robust radar-to-LiDAR place recognition framework compatible with single-chip, scanning, and 4D radars.<n>Experiments on four datasets demonstrate that RLPR achieves recognition accuracy with strong zero-shot generalization capabilities.
  arXiv  Detail & Related papers  (2026-03-09T03:28:44Z)
• Sim2Radar: Toward Bridging the Radar Sim-to-Real Gap with VLM-Guided Scene Reconstruction [2.3510064024442374]
  Sim2Radar is an end-to-end framework that synthesizes training radar data directly from single-view RGB images.<n>Sim2Radar reconstructs a material-aware 3D scene by combining monocular depth estimation, segmentation, and vision-language reasoning.<n> Evaluated on real-world indoor scenes, Sim2Radar improves downstream 3D radar perception via transfer learning.
  arXiv  Detail & Related papers  (2026-02-10T10:56:47Z)
• RadarGen: Automotive Radar Point Cloud Generation from Cameras [64.69976771710057]
  We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery.<n>RadarGen adapts efficient image-latent diffusion to the radar domain by representing radar measurements in bird's-eye-view form.<n>We show that RadarGen captures characteristic radar measurement distributions and reduces the gap to perception models trained on real data.
  arXiv  Detail & Related papers  (2025-12-19T18:57:33Z)
• Simulate Any Radar: Attribute-Controllable Radar Simulation via Waveform Parameter Embedding [12.285004244174917]
  SA-Radar is a radar simulation approach that enables controllable and efficient generation of radar cubes conditioned on customizable radar attributes.<n>We design ICFAR-Net, a 3D U-Net conditioned on radar attributes encoded via waveform parameters, which captures signal variations induced by different radar configurations.<n>Our framework also supports simulation in novel sensor viewpoints and edited scenes, showcasing its potential as a general-purpose radar data engine for autonomous driving applications.
  arXiv  Detail & Related papers  (2025-06-03T17:58:28Z)
• Deep Learning-based Target-To-User Association in Integrated Sensing and Communication Systems [8.401664608719633]
  We consider a radar-assisted communication system where a base station is equipped with a multiple-input-multiple-output (MIMO) radar. The proposed target-to-user (T2U) association consists of two stages. Joint multi-target detection and beam inference is obtained by modifying the you only look once (YOLO) model.
  arXiv  Detail & Related papers  (2024-01-11T00:45:33Z)
• Semantic Segmentation of Radar Detections using Convolutions on Point Clouds [59.45414406974091]
  We introduce a deep-learning based method to convolve radar detections into point clouds. We adapt this algorithm to radar-specific properties through distance-dependent clustering and pre-processing of input point clouds. Our network outperforms state-of-the-art approaches that are based on PointNet++ on the task of semantic segmentation of radar point clouds.
  arXiv  Detail & Related papers  (2023-05-22T07:09:35Z)
• Sionna RT: Differentiable Ray Tracing for Radio Propagation Modeling [65.17711407805756]
  Sionna is a GPU-accelerated open-source library for link-level simulations based on. Since release v0.14 it integrates a differentiable ray tracer (RT) for the simulation of radio wave propagation.
  arXiv  Detail & Related papers  (2023-03-20T13:40:11Z)
• Boosting 3D Object Detection by Simulating Multimodality on Point Clouds [51.87740119160152]
  This paper presents a new approach to boost a single-modality (LiDAR) 3D object detector by teaching it to simulate features and responses that follow a multi-modality (LiDAR-image) detector. The approach needs LiDAR-image data only when training the single-modality detector, and once well-trained, it only needs LiDAR data at inference. Experimental results on the nuScenes dataset show that our approach outperforms all SOTA LiDAR-only 3D detectors.
  arXiv  Detail & Related papers  (2022-06-30T01:44:30Z)
• Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images [96.66271207089096]
  FCOS-LiDAR is a fully convolutional one-stage 3D object detector for LiDAR point clouds of autonomous driving scenes. We show that an RV-based 3D detector with standard 2D convolutions alone can achieve comparable performance to state-of-the-art BEV-based detectors.
  arXiv  Detail & Related papers  (2022-05-27T05:42:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.