A tri-sensor camera-LiDAR-radar 3D visual grounding benchmark and a language-routed fusion model, TSFormer, that improves grounding accuracy over prior baselines.
Scanrefer: 3d object localiza- tion in rgb-d scans using natural language,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
dataset 1polarities
baseline 1representative citing papers
citing papers explorer
-
Talk2Sensors: 3D Visual Grounding in Autonomous Driving via Sensor-Adaptive Physical Cue Matching
A tri-sensor camera-LiDAR-radar 3D visual grounding benchmark and a language-routed fusion model, TSFormer, that improves grounding accuracy over prior baselines.