Viewpoint tokens learned on a mixed 3D-rendered and photorealistic dataset enable precise camera control in text-to-image generation while factorizing geometry from appearance and transferring to unseen object categories.
Score-based generative modeling through stochastic differential equa- tions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Camera Control for Text-to-Image Generation via Learning Viewpoint Tokens
Viewpoint tokens learned on a mixed 3D-rendered and photorealistic dataset enable precise camera control in text-to-image generation while factorizing geometry from appearance and transferring to unseen object categories.