arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.01649cs.CV
收藏

更好的引导者更好地预测未来:差异引导的生成对抗网络

Better Guider Predicts Future Better: Difference Guided Generative Adversarial Networks

Huazhong University of Science and Technology(华中科技大学);National University of Singapore(新加坡国立大学)

Guohao Ying, Yingtian Zou, Lin Wan, Yiming Hu, Jiashi Feng

摘要:

预测未来是一项充满幻想但很实用的工作。它是智能代理的关键组成部分,如自动驾驶汽车,医疗监控设备和机器人。在这项工作中,我们考虑从以前的obeservations,这是出了名的困难,由于帧动态的不确定性,生成看不见的未来帧。虽然最近基于生成对抗网络(GANs)的工作取得了显着进展,但仍然存在准确和现实预测的障碍。在本文中,我们提出了一种新的GAN帧间差分的基础上,以规避困难。更具体地说,我们的模型是一个多阶段生成网络,被称为差异引导生成对抗网络(DGGAN)。DGGAN学习明确地强制执行由合成帧间差异引导的未来帧预测。给定帧序列,DGGAN首先使用双路径来生成Meta信息。一条路径称为粗帧生成器,预测未来帧的粗细节,另一条路径称为差异指南生成器,生成包含互补细节的差异图像。然后,我们的粗细节,然后将通过差分图像的指导下,GANs的支持下,细化。有了这个模型和新颖的架构,我们实现了国家的最先进的性能,为未来的视频预测UCF-101,KITTI。

英文摘要:

Predicting the future is a fantasy but practicality work. It is the key component to intelligent agents, such as self-driving vehicles, medical monitoring devices and robotics. In this work, we consider generating unseen future frames from previous obeservations, which is notoriously hard due to the uncertainty in frame dynamics. While recent works based on generative adversarial networks (GANs) made remarkable progress, there is still an obstacle for making accurate and realistic predictions. In this paper, we propose a novel GAN based on inter-frame difference to circumvent the difficulties. More specifically, our model is a multi-stage generative network, which is named the Difference Guided Generative Adversarial Netwok (DGGAN). The DGGAN learns to explicitly enforce future-frame predictions that is guided by synthetic inter-frame difference. Given a sequence of frames, DGGAN first uses dual paths to generate meta information. One path, called Coarse Frame Generator, predicts the coarse details about future frames, and the other path, called Difference Guide Generator, generates the difference image which include complementary fine details. Then our coarse details will then be refined via guidance of difference image under the support of GANs. With this model and novel architecture, we achieve state-of-the-art performance for future video prediction on UCF-101, KITTI.

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。

↑