Image generation pretraining builds generalist vision models that reach SOTA on 2D and 3D perception tasks by reframing them as RGB image outputs.
Introducing nano banana pro
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Image Generators are Generalist Vision Learners
Image generation pretraining builds generalist vision models that reach SOTA on 2D and 3D perception tasks by reframing them as RGB image outputs.