Unit-robust text augmentation (3DTE) plus text-guided geometry attention (TGE) lifts monocular 3D visual grounding accuracy on Mono3DRefer, notably in far-range scenes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dual Enhancement on 3D Vision-Language Perception for Monocular 3D Visual Grounding
Unit-robust text augmentation (3DTE) plus text-guided geometry attention (TGE) lifts monocular 3D visual grounding accuracy on Mono3DRefer, notably in far-range scenes.