arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1607.02586cs.CVcs.LG
收藏

视觉动力学:通过交叉卷积网络的概率未来帧合成

Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks

Massachusetts Institute of Technology(麻省理工学院);Google Research(谷歌研究院)

Tianfan Xue, Jiajun Wu, Katherine L. Bouman, William T. Freeman

摘要:

我们研究的问题,从一个单一的输入图像合成的一些可能的未来帧。与传统的方法,这已经解决了这个问题,在一个确定性或非参数的方式,我们提出了一种新的方法,模型未来的帧在概率的方式。我们的概率模型使我们能够从单个输入图像中采样和合成许多可能的未来帧。未来的帧合成是具有挑战性的,因为它涉及低层次和高层次的图像和运动理解。我们提出了一种新的网络结构,即交叉卷积网络,以帮助合成未来的帧;这种网络结构将图像和运动信息分别编码为特征图和卷积核。在实验中,我们的模型表现良好的合成数据,如2D形状和动画游戏精灵,以及对现实世界的视频。我们还表明,我们的模型可以应用于任务,如视觉类比制作,并提出了一个学习的网络表示的分析。

英文摘要:

We study the problem of synthesizing a number of likely future frames from a single input image. In contrast to traditional methods, which have tackled this problem in a deterministic or non-parametric way, we propose a novel approach that models future frames in a probabilistic manner. Our probabilistic model makes it possible for us to sample and synthesize many possible future frames from a single input image. Future frame synthesis is challenging, as it involves low- and high-level image and motion understanding. We propose a novel network structure, namely a Cross Convolutional Network to aid in synthesizing future frames; this network structure encodes image and motion information as feature maps and convolutional kernels, respectively. In experiments, our model performs well on synthetic data, such as 2D shapes and animated game sprites, as well as on real-wold videos. We also show that our model can be applied to tasks such as visual analogy-making, and present an analysis of the learned network representations.

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。

↑