3D-Aware Video Generation
Abstract
Generative models have emerged as an essential building block for many image synthesis and editing tasks. Recent advances in this field have also enabled high-quality 3D or video content to be generated that exhibits either multi-view or temporal consistency. With our work, we explore 4D generative adversarial networks (GANs) that learn unconditional generation of 3D-aware videos. By combining neural implicit representations with time-aware discriminator, we develop a GAN framework that synthesizes 3D video supervised only with monocular videos. We show that our method learns a rich embedding of decomposable 3D structures and motions that enables new visual effects of spatio-temporal renderings while producing imagery with quality comparable to that of existing 3D or video GANs.
Cite
Text
Bahmani et al. "3D-Aware Video Generation." Transactions on Machine Learning Research, 2023.Markdown
[Bahmani et al. "3D-Aware Video Generation." Transactions on Machine Learning Research, 2023.](https://mlanthology.org/tmlr/2023/bahmani2023tmlr-3daware/)BibTeX
@article{bahmani2023tmlr-3daware,
title = {{3D-Aware Video Generation}},
author = {Bahmani, Sherwin and Park, Jeong Joon and Paschalidou, Despoina and Tang, Hao and Wetzstein, Gordon and Guibas, Leonidas and Van Gool, Luc and Timofte, Radu},
journal = {Transactions on Machine Learning Research},
year = {2023},
url = {https://mlanthology.org/tmlr/2023/bahmani2023tmlr-3daware/}
}