7 papers
DNOI-4DRO: Deep 4D Radar Odometry with Differentiable Neural-Optimization Iterations
Shouyi Lu, Huanyu Zhou, Guirong Zhuo +1
A novel learning-optimization-combined 4D radar odometry model, named DNOI-4DRO, is proposed in this paper. The proposed model seamlessly integrates traditional geometric optimizat…
Diff-GNSS: Diffusion-based Pseudorange Error Estimation
Jiaqi Zhu, Shouyi Lu, Ziyao Li +2
Global Navigation Satellite Systems (GNSS) are vital for reliable urban positioning. However, multipath and non-line-of-sight reception often introduce large measurement errors tha…
MSDNet: Efficient 4D Radar Super-Resolution via Multi-Stage Distillation
Minqing Huang, Shouyi Lu, Boyuan Zheng +3
4D radar super-resolution, which aims to reconstruct sparse and noisy point clouds into dense and geometrically consistent representations, is a foundational problem in autonomous…
4DRadar-GS: Self-Supervised Dynamic Driving Scene Reconstruction with 4D Radar
Xiao Tang, Guirong Zhuo, Cong Wang +5
3D reconstruction and novel view synthesis are critical for validating autonomous driving systems and training advanced perception models. Recent self-supervised methods have gaine…
MultiEditor: Controllable Multimodal Object Editing for Driving Scenarios Using 3D Gaussian Splatting Priors
Shouyi Lu, Zihan Lin, Chao Lu +3
Autonomous driving systems rely heavily on multimodal perception data to understand complex environments. However, the long-tailed distribution of real-world data hinders generaliz…
R2LDM: An Efficient 4D Radar Super-Resolution Framework Leveraging Diffusion Model
Boyuan Zheng, Shouyi Lu, Renbo Huang +5
We introduce R2LDM, an innovative approach for generating dense and accurate 4D radar point clouds, guided by corresponding LiDAR point clouds. Instead of utilizing range images or…