Oct 2026· IEEE Robotics and Automation Letters· Vol 11, pp. 12112-12119· 0 citations· 40 references
Computer Science
TL;DR
The Kinematic Compensation Temporal Fusion Network (KCTF-Net), a novel 3D detection framework that explicitly aligns dynamic points in physical space, rectifying the motion-induced “smearing” effect, is proposed.
Abstract
4D millimeter-wave (mmWave) radar enables all-weather 3D object detection with reliable Doppler sensing. However, its practical application is hindered by inherent sparsity and noise. While multi-frame accumulation densifies point clouds, it inevitably introduces motion-induced spatiotemporal misalignment and geometric distortion, degrading detection accuracy in dynamic environments. To address these challenges, we propose the Kinematic Compensation Temporal Fusion Network (KCTF-Net), a novel 3D detection framework. Specifically, the Dynamic Kinematic Compensation (DKC) module explicitly aligns dynamic points in physical space, rectifying the motion-induced “smearing” effect. Furthermore, the Temporal Pillar Flow Enhancement (TPFE) module captures latent inter-frame kinematics, adaptively suppressing noise and mitigating sparsity. Finally, the Motion-Guided Attention Fusion (MGAF) module synergistically integrates density-filtered geometric priors with temporal features to reconstruct precise object geometries. Extensive experiments on the View-of-Delft (VoD) and TJ4DRadSet benchmarks demonstrate that KCTF-Net achieves state-of-the-art performance. Notably, it yields a 3D mean average precision (mAP) of 57.73%.
While the fusion of 4D millimeter-wave radar and camera holds significant potential for 3D object detection in autonomous driving, the extreme sparsity of radar points and the deficiency of depth information in images lead to severe cross-modal spatial misalignment. Existing two-stage methods might suffer from the irre...
Yu-Zhe Song, De-Xing Lin, Jian Chen et al.· 0 citations
A hierarchical context-detail enhancement (HCDE) framework to address challenges in local detail representation and long-range context modeling of 4D millimeter-wave radar, and designs a radar attribute-aware encoding (RAE) module to enable local detail modeling.
Hang Yan, Xiao-Kai Bai, Pei Cheng et al.· IEEE Robotics and Automation...· 0 citations
In spaceborne inverse synthetic aperture radar (ISAR) imaging of high-speed space targets, the high orbital velocities of the radar and target can result in pronounced translational motion. Meanwhile, the large relative radial velocity makes intra-pulse motion nonnegligible, causing high-resolution range profile (HRRP)...
He Ni, Yi-Cheng Jiang· IEEE Geoscience and Remote S...· 0 citations
LiDAR--4-D radar fusion combines accurate spatial geometry with motion and reflectivity cues from radar, offering a promising solution for 3-D object detection in complex driving environments. However, sparse radar observations and differences in spatial sampling between the two modalities complicate reliable cross-mod...
Gang Ma, Sen-Jie Hu, Jun-Jie Liu et al.· arXiv.org· 0 citations
Radar-camera fusion combines visual semantics with reliable radial depth and Doppler velocity for 3D object detection in autonomous driving. However, sparse and noisy radar measurements, cross-frame misalignment of dynamic objects, and cross-modal semantic discrepancies and reliability variations hinder robust fusion....
Ze Zhou, Run-Nan Zhou, Xiang-Hao Zhou et al.· 0 citations