4DRadar-GS: Self-Supervised Dynamic Driving Scene Reconstruction with 4D Radar
This addresses the challenge of reconstructing dynamic driving scenes for autonomous driving validation and perception training, representing an incremental improvement over existing methods.
The paper tackles the problem of inaccurate dynamic object reconstruction in self-supervised 3D reconstruction for autonomous driving by proposing 4DRadar-GS, a framework that uses 4D radar data for initialization and tracking, achieving state-of-the-art performance on the OmniHD-Scenes dataset.
3D reconstruction and novel view synthesis are critical for validating autonomous driving systems and training advanced perception models. Recent self-supervised methods have gained significant attention due to their cost-effectiveness and enhanced generalization in scenarios where annotated bounding boxes are unavailable. However, existing approaches, which often rely on frequency-domain decoupling or optical flow, struggle to accurately reconstruct dynamic objects due to imprecise motion estimation and weak temporal consistency, resulting in incomplete or distorted representations of dynamic scene elements. To address these challenges, we propose 4DRadar-GS, a 4D Radar-augmented self-supervised 3D reconstruction framework tailored for dynamic driving scenes. Specifically, we first present a 4D Radar-assisted Gaussian initialization scheme that leverages 4D Radar's velocity and spatial information to segment dynamic objects and recover monocular depth scale, generating accurate Gaussian point representations. In addition, we propose a Velocity-guided PointTrack (VGPT) model, which is jointly trained with the reconstruction pipeline under scene flow supervision, to track fine-grained dynamic trajectories and construct temporally consistent representations. Evaluated on the OmniHD-Scenes dataset, 4DRadar-GS achieves state-of-the-art performance in dynamic driving scene 3D reconstruction.