PillarDETR uses a CSP YOLOv8 backbone and RT-DETR head on pillar pseudoimages for real-time 3D object detection, reporting improved mAP-latency trade-off on KITTI and nuScenes over PointPillars.
Going beyond density functional theory accuracy: Leveraging experimental data to refine pre-trained machine learning interatomic potentials,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PillarDETR: YOLO-Backbone and RT-DETR Head for Real-Time 3D Object Detection
PillarDETR uses a CSP YOLOv8 backbone and RT-DETR head on pillar pseudoimages for real-time 3D object detection, reporting improved mAP-latency trade-off on KITTI and nuScenes over PointPillars.