UniSpace-3D reports state-of-the-art 3D visual grounding accuracy by mapping point clouds and text into a shared CLIP space and adding contrastive losses and language-guided query selection.
Towards subjective quality assessment of point cloud imaging in augmented reality,
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
unclear 1representative citing papers
citing papers explorer
-
Unified Representation Space for 3D Visual Grounding
UniSpace-3D reports state-of-the-art 3D visual grounding accuracy by mapping point clouds and text into a shared CLIP space and adding contrastive losses and language-guided query selection.