Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise

Generative modeling aims to transform random noise into structured outputs. In this work, we enhance video diffusion models by allowing motion control via structured latent noise sampling. This is achieved by just a change in data: we pre-process training videos to yield structured noise. Consequent...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Burgert, Ryan, Xu, Yuancheng, Xian, Wenqi, Pilarski, Oliver, Clausen, Pascal, He, Mingming, Ma, Li, Deng, Yitong, Li, Lingxiao, Mousavi, Mohsen, Ryoo, Michael, Debevec, Paul, Yu, Ning
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!