James Burgess*

Viewpoint textual inversion: discovering scene representations and 3D view control in 2D diffusion models

"Text-to-image diffusion models generate impressive and realistic images, but do they learn to represent the 3D world from only 2D supervision? We demonstrate that yes, certain 3D scene representations are encoded in the text embedding space of models like Stable Diffusion. Our approach, Viewpoint N…