Reproducing and Extending RaDelft 4D Radar with Camera-Assisted Labels
This work addresses a reproducibility and data bottleneck for researchers in radar semantic segmentation, though it is incremental by extending existing methods with camera assistance.
The authors tackled the scarcity of open-source labeled 4D radar datasets by reproducing RaDelft's results and developing a camera-guided labeling pipeline that generates accurate radar labels without human annotations, achieving significant accuracy improvements. They also quantified the impact of fog levels on labeling performance.
Recent advances in 4D radar highlight its potential for robust environment perception under adverse conditions, yet progress in radar semantic segmentation remains constrained by the scarcity of open source datasets and labels. The RaDelft data set, although seminal, provides only LiDAR annotations and no public code to generate radar labels, limiting reproducibility and downstream research. In this work, we reproduce the numerical results of the RaDelft group and demonstrate that a camera-guided radar labeling pipeline can generate accurate labels for radar point clouds without relying on human annotations. By projecting radar point clouds into camera-based semantic segmentation and applying spatial clustering, we create labels that significantly enhance the accuracy of radar labels. These results establish a reproducible framework that allows the research community to train and evaluate the labeled 4D radar data. In addition, we study and quantify how different fog levels affect the radar labeling performance.