EVT achieves state-of-the-art 75.3% NDS on the nuScenes test set by using LiDAR-guided adaptive sampling and projection for image-to-BEV transformation, along with a geometry-aware transformer decoder.
Objectfusion: Multi-modal 3d object detection with object-centric fusion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EVT: Efficient View Transformation for Multi-Modal 3D Object Detection
EVT achieves state-of-the-art 75.3% NDS on the nuScenes test set by using LiDAR-guided adaptive sampling and projection for image-to-BEV transformation, along with a geometry-aware transformer decoder.