Enabling Visual Composition and Animation in Unsupervised Video Generation

Autor:	Davtyan, Aram, Sameni, Sepehr, Ommer, Björn, Favaro, Paolo
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	In this work we propose a novel method for unsupervised controllable video generation. Once trained on a dataset of unannotated videos, at inference our model is capable of both composing scenes of predefined object parts and animating them in a plausible and controlled way. This is achieved by conditioning video generation on a randomly selected subset of local pre-trained self-supervised features during training. We call our model CAGE for visual Composition and Animation for video GEneration. We conduct a series of experiments to demonstrate capabilities of CAGE in various settings. Project website: https://araachie.github.io/cage. Comment: Project website: https://araachie.github.io/cage
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2403.14368 Zobrazit plný text záznamu View this record from Arxiv