G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding
Open paper
Benchmark
Model
Rank
Results
3d-visual-grounding-on-scanrefer-val
G3-LQ (Two-Stage)
–
Acc@0.25: 56.9
Acc@0.5: 45.58
Rank counts only results with a code link.