GaussianDet3D is presented, the first method to apply 3D Gaussian Splatting from multi-view images to 3D object detection in the context of autonomous driving, treating predicted Gaussian primitives as a pseudo-LiDAR point cloud fed into a sparse LiDAR detector.
Results validate the effectiveness of the proposed novel 3D object detection and tracking framework, termed ECF3DMOT, in advancing 3D object detection and tracking for autonomous driving.
Xiaojuan Peng, Fei Teng, Tiankai Chen et al.· International Journal of Mac...· 0 citations
Recent studies highlight the effectiveness of 3D Gaussian splatting (3DGS) in visual simultaneous localization and mapping (SLAM) systems, which work well indoors but struggle in large-scale outdoor environments. Typically, lidar data are used to address this issue; however, current multi-modal SLAM systems use 3DGS ma...
This paper proposes LV-GS SLAM, a novel system that integrates LiDAR and visual data for incremental, large-scale reconstruction with real-time tracking, and develops a keyframe-based submap management framework that dynamically adjusts memory allocation based on both primitive density and inter-frame overlap ratio, ef...
PES-PointPillars is presented, an enhanced PointPillars detector with three coordinated design changes, with the complete model providing the strongest aggregate performance among the evaluated configurations.
GARF, a geometry-aware polar BEV framework, is presented for multi-modal 3D object detection, which organizes camera and LiDAR features in a unified polar BEV space, which can represent spatial resolution more compactly and achieve effective feature interaction and consistent geometry supervision.
Feng Gao, Jiaxin Chen, Niuniu Wang· Italian National Conference...· 0 citations
OccBEV-Oracle, a lightweight completion neck inserted between the BEV backbone and dense head of a CenterPoint-style detector, and a direct measurement of where the neck edits the BEV map, show that the aligned GT-ROM mask itself supplies a strong localization prior.
Jun Wang, Quanxin Zheng, Jian-Ping Yu· IEEE Access· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
