SPAZER, a VLM-driven agent, combines 3D rendered views with 2D camera images in a progressive pipeline to achieve state-of-the-art zero-shot 3D visual grounding.
Spatial and object visualization cognitive styles: Validation studies in 3800 individuals
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
support 1representative citing papers
citing papers explorer
-
SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding
SPAZER, a VLM-driven agent, combines 3D rendered views with 2D camera images in a progressive pipeline to achieve state-of-the-art zero-shot 3D visual grounding.