A two-stage cross-view fusion network for 4D radar and camera achieves new state-of-the-art 3D detection accuracy on VoD and TJ4DRadSet, and is the first radar-camera fusion method to match a LiDAR-based detector on VoD.
Point density-aware voxels for lidar 3d object detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
CVFusion: Cross-View Fusion of 4D Radar and Camera for 3D Object Detection
A two-stage cross-view fusion network for 4D radar and camera achieves new state-of-the-art 3D detection accuracy on VoD and TJ4DRadSet, and is the first radar-camera fusion method to match a LiDAR-based detector on VoD.