DiffDreamer: View Generation with Conditional Diffusion Models | ICCV 2023

ABSTRACT

Perpetual view generation-the task of generating long-range novel views by flying into a given image-has been a novel yet promising task. We introduce DiffDreamer, an unsupervised framework capable of synthesizing novel views depicting a long camera trajectory while training solely on internet-collected images of nature scenes. We demonstrate that image-conditioned diffusion models can effectively perform long-range scene extrapolation while preserving both local and global consistency significantly better than prior GAN-based methods.

FILES

• Technical paper and supplement (link to arxiv)
• Project Website (link)

CITATION

S. Cai, E. R. Chan, S. Peng, M. Shahbazi, A. Obukhov, L. Van Gool, G. Wetzstein, DiffDreamer: Consistent Single-view Perpetual View Generation with Conditional Diffusion Models, ICCV 2023.

@inproceedings{cai2022diffdreamer,
author = {S. Cai and E. R. Chan and S. Peng and M. Shahbazi and A. Obukhov and L. Van Gool and G. Wetzstein},
title = {DiffDreamer: Consistent Single-view Perpetual View Generation with Conditional Diffusion Models},
booktitle = {ICCV},
year = {2022},
}