arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.08522cs.CV
收藏

合成视频预测

Compositional Video Prediction

Verisk Analytics(Verisk分析公司);Carnegie Mellon University(卡内基梅隆大学);Facebook AI Research(Facebook人工智能研究院)

Yufei Ye, Maneesh Singh, Abhinav Gupta, Shubham Tulsiani

摘要:

我们提出了一个像素级的未来预测给定的场景的输入图像的方法。我们观察到,一个场景是由不同的实体,经历运动,并提出了一种方法,操作化这一见解。我们隐式地预测独立实体的未来状态,同时推理它们的相互作用,并使用这些预测的状态组成未来的视频帧。我们克服了固有的多模态的任务,使用一个全球性的概率水平的潜在随机变量,并表明,这使我们能够样本多样化和合理的未来。我们经验验证我们的方法对替代表示和方式,将多模态。我们检查了两个数据集,一个包含可能会掉落的堆叠对象,另一个包含人类在健身房进行活动的视频,并表明我们的方法允许在这些不同的设置中进行逼真的随机视频预测。有关视频预测,请参见https://judyye.github.io/CVP/。

英文摘要:

We present an approach for pixel-level future prediction given an input image of a scene. We observe that a scene is comprised of distinct entities that undergo motion and present an approach that operationalizes this insight. We implicitly predict future states of independent entities while reasoning about their interactions, and compose future video frames using these predicted states. We overcome the inherent multi-modality of the task using a global trajectory-level latent random variable, and show that this allows us to sample diverse and plausible futures. We empirically validate our approach against alternate representations and ways of incorporating multi-modality. We examine two datasets, one comprising of stacked objects that may fall, and the other containing videos of humans performing activities in a gym, and show that our approach allows realistic stochastic video prediction across these diverse settings. See https://judyye.github.io/CVP/ for video predictions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑