BriefGPT.xyz
Aug, 2020
DeepLandscape：风景视频的对抗建模
DeepLandscape: Adversarial Modeling of Landscape Video
HTML
PDF
Elizaveta Logacheva, Roman Suvorov, Oleg Khomenko, Anton Mashikhin, Victor Lempitsky
TL;DR
本文利用模型 StyleGAN 对风景视频进行训练，生成真实的时间变化风景视频，并通过拟合到静态风景图像中实现再现，同时提出简单的 StyleGAN 反演过程改进，生成比以前更引人注目的风景动画。
Abstract
We build a new model of
landscape videos
that can be trained on a mixture of static landscape images as well as landscape animations. Our architecture extends
stylegan
model by augmenting it with parts that allow
→