UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection

Open paper
Benchmark Model Rank Results
3d-object-detection-on-argoverse-2-3d-object-detectionUniMamba–mAP: 42.0
3d-object-detection-on-nuscenesUniMamba–NDS: 0.740mAP: 0.702
3d-object-detection-on-waymo-open-datasetUniMamba–mAPH/L2: 74.11

Rank counts only results with a code link.