SPAD: Spatially Aware Multiview Diffusers
Yash Kant
UofToronto & Vector
Ziyi Wu
UofToronto & Vector
Michael Vasilkovsky
Snap Research
Guocheng Qian
KAUST
Jian Ren
Snap Research
Riza Alp Guler
Snap Research
Bernard Ghanem
KAUST
Sergey Tulyakov*
Snap Research
Igor Gilitschenski*
UofToronto & Vector
Aliaksandr Siarohin*
Snap Research
tl;dr
Citation
Overview: SPAD
Given a text prompt, our method synthesizes 3D consistent views of the same object. Our model can generate many images from arbitrary camera viewpoints, while being trained only o...
Read more at yashkant.github.io