Search papers, labs, and topics across Lattice.
DualViewMapDet is a camera-only 3D object detection and tracking framework that leverages static point cloud maps from prior traversals to improve localization accuracy in the absence of LiDAR. The method employs a dual-space camera-map fusion strategy, projecting the map into perspective view (PV) for image feature enrichment and encoding it directly in bird's-eye view (BEV) for fusion with lifted camera features. Experiments on nuScenes and Argoverse 2 datasets demonstrate significant improvements over camera-only baselines, particularly in object localization.
Ditch the LiDAR: This camera-only method uses pre-built point cloud maps to drastically improve 3D object detection and tracking, rivaling LiDAR-based systems in familiar environments.
Camera-based 3D object detection and tracking are central to autonomous driving, yet precise 3D object localization remains fundamentally constrained by depth ambiguity when no expensive, depth-rich online LiDAR is available at inference. In many deployments, however, vehicles repeatedly traverse the same environments, making static point cloud maps from prior traversals a practical source of geometric priors. We propose DualViewMapDet, a camera-only inference framework that retrieves such map priors online and leverages them to mitigate the absence of a LiDAR sensor during deployment. The key idea is a dual-space camera-map fusion strategy that avoids one-sided view conversion. Specifically, we (i) project the map into perspective view (PV) and encode multi-channel geometric cues to enrich image features and support BEV lifting, and (ii) encode the map directly in bird's-eye view (BEV) with a sparse voxel backbone and fuse it with lifted camera features in a shared metric space. Extensive evaluations on nuScenes and Argoverse 2 demonstrate consistent improvements over strong camera-only baselines, with particularly strong gains in object localization. Ablations further validate the contributions of PV/BEV fusion and prior-map coverage. We make the code and pre-trained models available at https://dualviewmapdet.cs.uni-freiburg.de .
