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 1706.01433cs.CV
收藏

视觉交互网络

Visual Interaction Networks

DeepMind

Nicholas Watters, Andrea Tacchetti, Theophane Weber, Razvan Pascanu, Peter Battaglia, Daniel Zoran

摘要:

仅仅通过一瞥,人类就可以对各种物理系统的未来状态做出丰富的预测。另一方面,来自工程、机器人和图形学的现代方法通常局限于狭窄的领域,需要直接测量底层状态。我们介绍了视觉交互网络,一个通用的模型,用于从原始的视觉观察中学习物理系统的动态。我们的模型由一个基于卷积神经网络的感知前端和一个基于交互网络的动态预测器组成。通过联合训练,感知前端学会将动态视觉场景解析为一组分解的潜在对象表示。动态预测器通过计算它们的相互作用和动态来学习及时向前滚动这些状态,从而产生任意长度的预测物理轨迹。我们发现,仅从六个输入视频帧,视觉交互网络就可以在各种物理系统上生成数百个时间步长的精确未来轨迹。我们的模型还可以应用于具有不可见物体的场景,根据它们对可见物体的影响来推断它们的未来状态,并且可以隐式地推断物体的未知质量。我们的研究结果表明,感知模块和基于对象的动态预测模块可以诱导因子化的潜在表示,支持准确的动态预测。这项工作为基于模型的决策和规划提供了新的机会,这些决策和规划来自复杂物理环境中的原始感官观察。

英文摘要:

From just a glance, humans can make rich predictions about the future state of a wide range of physical systems. On the other hand, modern approaches from engineering, robotics, and graphics are often restricted to narrow domains and require direct measurements of the underlying states. We introduce the Visual Interaction Network, a general-purpose model for learning the dynamics of a physical system from raw visual observations. Our model consists of a perceptual front-end based on convolutional neural networks and a dynamics predictor based on interaction networks. Through joint training, the perceptual front-end learns to parse a dynamic visual scene into a set of factored latent object representations. The dynamics predictor learns to roll these states forward in time by computing their interactions and dynamics, producing a predicted physical trajectory of arbitrary length. We found that from just six input video frames the Visual Interaction Network can generate accurate future trajectories of hundreds of time steps on a wide range of physical systems. Our model can also be applied to scenes with invisible objects, inferring their future states from their effects on the visible objects, and can implicitly infer the unknown mass of objects. Our results demonstrate that the perceptual module and the object-based dynamics predictor module can induce factored latent representations that support accurate dynamical predictions. This work opens new opportunities for model-based decision-making and planning from raw sensory observations in complex physical environments.

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。

↑