You're currently viewing an old version of this dataset. To see the current version, click here.

EscherNet: A Generative Model for Scalable View Synthesis

EscherNet is a multi-view conditioned diffusion model designed for scalable view synthesis. It leverages Stable Diffusion's 2D architecture empowered by the innovative Camera Positional Embedding (CaPE), EscherNet adeptly learns implicit 3D representations from varying number of reference views, achieving consistent 3D novel view synthesis.

Data and Resources

Cite this as

Xin Kong, Shikun Liu, Xiaoyang Lyu, Marwan Taher, Xiaojuan Qi, Andrew J. Davison (2024). Dataset: EscherNet: A Generative Model for Scalable View Synthesis. https://doi.org/10.57702/qhbmtyy6

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2402.03908
Author Xin Kong
More Authors
Shikun Liu
Xiaoyang Lyu
Marwan Taher
Xiaojuan Qi
Andrew J. Davison
Homepage https://kxhit.github.io/EscherNet