Generating Long Videos of Dynamic Scenes

作者：Tim Brooks, Janne Hellsten, M. Aittala, Ting-Chun Wang, Timo Aila, J. Lehtinen, Ming-Yu Liu, Alexei A. Efros, Tero Karras · 发表于：Neural Information Processing Systems · 年份：2022 · DOI：10.48550/arxiv.2206.03429 · 被引用次数：151 · 研究领域：Computer Science

We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time while maintaining consistencies expected in real environments, such as plausible dynamics and object persistence. A common failure case is for content to never change due to over-reliance on inductive biases to provide temporal consistency, such as a single latent code that dictates content for the entire video. On the other extreme, without long-term consistency, generated videos may morph unrealistically between different scenes. To address these limitations, we prioritize the time axis by redesigning the temporal latent representation and learning long-term consistency from data by training on longer videos. To this end, we leverage a two-phase training strategy, where we separately train using longer videos at a low resolution and shorter videos at a high resolution. To evaluate the capabilities of our model, we introduce two new benchmark datasets with explicit focus on long-term temporal dynamics.