The paper builds a training-free, open-vocabulary 3D detector by lifting GroundingDINO and SAM 2D proposals into LiDAR or pseudo-depth point clouds, reaching about 30% mAP on nuScenes mini.
Lvis: A dataset for large vocabulary instance segmentation
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
background 1representative citing papers
citing papers explorer
-
Just Add Geometry: Gradient-Free Open-Vocabulary 3D Detection Without Human-in-the-Loop
The paper builds a training-free, open-vocabulary 3D detector by lifting GroundingDINO and SAM 2D proposals into LiDAR or pseudo-depth point clouds, reaching about 30% mAP on nuScenes mini.