Pith. sign in

Which of the panels contains an object with an identical 3D shape to the object in panel A. Your answer must come as a single letter

Testing the models To test the model's ability to recognize 3D shapes we create a four-panel image (Figure 1-6)

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.CV 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Do large language vision models understand 3D shapes?

cs.CV · 2024-12-14 · conditional · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Do large language vision models understand 3D shapes? cs.CV · 2024-12-14 · conditional · none · ref 7

    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.