3D-Aware Video Generation

Published: 07 Jun 2023, Last Modified: 07 Jun 2023Accepted by TMLREveryoneRevisionsBibTeX
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.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: - Acknowledged limitation of 2D upsampling layers decreasing 3D consistency - Added geometry evaluation results - Visualized TaiChi depth maps - Clarified hyperparameter selection - Clarified inductive bias for motion/content disentanglement - Clarified missing ACD and CPBD metrics - Updated Fig. 2 - Added missing references - Fixed equations - Fixed citations
Code: https://github.com/sherwinbahmani/3dvideogeneration/
Supplementary Material: zip
Assigned Action Editor: ~Mathieu_Salzmann1
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Number: 791