RadarXFormer: Robust Object Detection via Cross-Dimension Fusion of 4D Radar Spectra and Images for Autonomous Driving

• URL: http://arxiv.org/abs/2603.14822v1
• Date: Mon, 16 Mar 2026 04:56:37 GMT
• Title: RadarXFormer: Robust Object Detection via Cross-Dimension Fusion of 4D Radar Spectra and Images for Autonomous Driving
• Abstract summary: Camera- and LiDAR-based perception systems suffer from performance degradation under adverse weather and lighting conditions.<n>Radar-vision fusion provides a promising alternative by combining the environmental robustness and cost efficiency of millimeter-wave (mmWave) radar with the rich semantic information captured by cameras.<n>This paper proposes RadarXFormer, a 3D object detection framework that enables efficient cross-modal fusion between 4D radar spectra and RGB images.
• Score: 28.09294325639777
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reliable perception is essential for autonomous driving systems to operate safely under diverse real-world traffic conditions. However, camera- and LiDAR-based perception systems suffer from performance degradation under adverse weather and lighting conditions, limiting their robustness and large-scale deployment in intelligent transportation systems. Radar-vision fusion provides a promising alternative by combining the environmental robustness and cost efficiency of millimeter-wave (mmWave) radar with the rich semantic information captured by cameras. Nevertheless, conventional 3D radar measurements lack height resolution and remain highly sparse, while emerging 4D mmWave radar introduces elevation information but also brings challenges such as signal noise and large data volume. To address these issues, this paper proposes RadarXFormer, a 3D object detection framework that enables efficient cross-modal fusion between 4D radar spectra and RGB images. Instead of relying on sparse radar point clouds, RadarXFormer directly leverages raw radar spectra and constructs an efficient 3D representation that reduces data volume while preserving complete 3D spatial information. The "X" highlights the proposed cross-dimension (3D-2D) fusion mechanism, in which multi-scale 3D spherical radar feature cubes are fused with complementary 2D image feature maps. Experiments on the K-Radar dataset demonstrate improved detection accuracy and robustness under challenging conditions while maintaining real-time inference capability.

Related papers

• RadarSim: Simulating Single-Chip Radar via Multimodal Neural Fields [49.41438378775056]
  Radars are an ideal complement to cameras, with cameras offering fine angular resolution and radars providing metric depth and robustness under adverse weather.<n>RadarSim produces sharper geometry and Doppler range frames than radar-only reconstructions.
  arXiv  Detail & Related papers  (2026-05-25T21:03:40Z)
• Wavelet-based Multi-View Fusion of 4D Radar Tensor and Camera for Robust 3D Object Detection [44.78575994732947]
  WRCFormer is a novel 3D object detection framework that fuses raw radar cubes with camera inputs via multi-view representations of the decoupled radar cube.<n>WRCFormer achieves state-of-the-art performance on the K-Radar benchmarks, surpassing the best model by approximately 2.4% in all scenarios.
  arXiv  Detail & Related papers  (2025-12-28T15:32:17Z)
• 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)
• Depth-aware Fusion Method based on Image and 4D Radar Spectrum for 3D Object Detection [32.96725310200148]
  3D millimeter-wave radars can only provide range, Doppler, and azimuth information for objects.<n>This paper leverages these two highly complementary and cost-effective sensors, 4D millimeter-wave radar and camera.<n>We propose using GAN-based networks to generate depth images from radar spectra in the absence of depth sensors.
  arXiv  Detail & Related papers  (2025-02-21T15:14:30Z)
• RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object Detection [68.99784784185019]
  Poor lighting or adverse weather conditions degrade camera performance.<n>Radar suffers from noise and positional ambiguity.<n>We propose RobuRCDet, a robust object detection model in BEV.
  arXiv  Detail & Related papers  (2025-02-18T17:17:38Z)
• TransRAD: Retentive Vision Transformer for Enhanced Radar Object Detection [6.163747364795787]
  We present TransRAD, a novel 3D radar object detection model.<n>We propose Location-Aware NMS to mitigate the common issue of duplicate bounding boxes in deep radar object detection.<n>Results demonstrate that TransRAD outperforms state-of-the-art methods in both 2D and 3D radar detection tasks.
  arXiv  Detail & Related papers  (2025-01-29T20:21:41Z)
• V2X-R: Cooperative LiDAR-4D Radar Fusion with Denoising Diffusion for 3D Object Detection [64.93675471780209]
  We present V2X-R, the first simulated V2X dataset incorporating LiDAR, camera, and 4D radar.<n>V2X-R contains 12,079 scenarios with 37,727 frames of LiDAR and 4D radar point clouds, 150,908 images, and 170,859 annotated 3D vehicle bounding boxes.<n>We propose a novel cooperative LiDAR-4D radar fusion pipeline for 3D object detection and implement it with various fusion strategies.
  arXiv  Detail & Related papers  (2024-11-13T07:41:47Z)
• RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar [15.776076554141687]
  3D occupancy-based perception pipeline has significantly advanced autonomous driving. Current methods rely on LiDAR or camera inputs for 3D occupancy prediction. We introduce a novel approach that utilizes 4D imaging radar sensors for 3D occupancy prediction.
  arXiv  Detail & Related papers  (2024-05-22T21:48:17Z)
• Radar Fields: Frequency-Space Neural Scene Representations for FMCW Radar [62.51065633674272]
  We introduce Radar Fields - a neural scene reconstruction method designed for active radar imagers. Our approach unites an explicit, physics-informed sensor model with an implicit neural geometry and reflectance model to directly synthesize raw radar measurements. We validate the effectiveness of the method across diverse outdoor scenarios, including urban scenes with dense vehicles and infrastructure.
  arXiv  Detail & Related papers  (2024-05-07T20:44:48Z)
• SMURF: Spatial Multi-Representation Fusion for 3D Object Detection with 4D Imaging Radar [12.842457981088378]
  This paper introduces spatial multi-representation fusion (SMURF), a novel approach to 3D object detection using a single 4D imaging radar. SMURF mitigates measurement inaccuracy caused by limited angular resolution and multi-path propagation of radar signals. Experimental evaluations on View-of-Delft (VoD) and TJ4DRadSet datasets demonstrate the effectiveness and generalization ability of SMURF.
  arXiv  Detail & Related papers  (2023-07-20T11:33:46Z)
• RadarNet: Exploiting Radar for Robust Perception of Dynamic Objects [73.80316195652493]
  We tackle the problem of exploiting Radar for perception in the context of self-driving cars. We propose a new solution that exploits both LiDAR and Radar sensors for perception. Our approach, dubbed RadarNet, features a voxel-based early fusion and an attention-based late fusion.
  arXiv  Detail & Related papers  (2020-07-28T17:15:02Z)

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.