HyperDet: 3D Object Detection with Hyper 4D Radar Point Clouds
This work addresses the challenge of cost-effective and weather-robust 3D detection for autonomous vehicles, though it is incremental as it builds on existing LiDAR-oriented detectors without architectural changes.
The paper tackled the problem of 3D object detection using sparse and noisy 4D radar point clouds, which lag behind LiDAR-based systems, by proposing HyperDet, a framework that aggregates and refines radar data to improve detection performance, achieving consistent improvements on the MAN TruckScenes dataset and partially narrowing the radar-LiDAR gap.
4D mmWave radar provides weather-robust, velocity-aware measurements and is more cost-effective than LiDAR. However, radar-only 3D detection still trails LiDAR-based systems because radar point clouds are sparse, irregular, and often corrupted by multipath noise, yielding weak and unstable geometry. We present HyperDet, a detector-agnostic radar-only 3D detection framework that constructs a task-aware hyper 4D radar point cloud for standard LiDAR-oriented detectors. HyperDet aggregates returns from multiple surround-view 4D radars over consecutive frames to improve coverage and density, then applies geometry-aware cross-sensor consensus validation with a lightweight self-consistency check outside overlap regions to suppress inconsistent returns. It further integrates a foreground-focused diffusion module with training-time mixed radar-LiDAR supervision to densify object structures while lifting radar attributes (e.g., Doppler, RCS); the model is distilled into a consistency model for single-step inference. On MAN TruckScenes, HyperDet consistently improves over raw radar inputs with VoxelNeXt and CenterPoint, partially narrowing the radar-LiDAR gap. These results show that input-level refinement enables radar to better leverage LiDAR-oriented detectors without architectural modifications.