A large synthetic benchmark shows vision-language models match 3D shapes well across single changes like rotation or texture, but fail when rotation and texture change together, trailing humans by a wide margin.
2) Has a different orientation compared to the object in panel A
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Do large language vision models understand 3D shapes?
A large synthetic benchmark shows vision-language models match 3D shapes well across single changes like rotation or texture, but fail when rotation and texture change together, trailing humans by a wide margin.