👨‍👩‍👦

未来を予測して動画を生成 – Generating Videos with Scene Dynamics –

Entry
未来を予測して動画を生成 – Generating Videos with Scene Dynamics –
Simple Title
Generating Videos with Scene Dynamics
Type
Project
Posted at
April 30, 2017
Tags
visualimage
Year
2017
image

Overview

一枚の画像から、前景背景を推定し、その画像の次の1〜2秒の動画を生成する研究です。

We capitalize on large amounts of unlabeled video in order to learn a model of scene dynamics for both video recognition tasks (e.g. action classification) and video generation tasks (e.g. future prediction). We propose a generative adversarial network for video with a spatio-temporal convolutional architecture that untangles the scene’s foreground from the background. Experiments suggest this model can generate tiny videos up to a second at full frame rate better than simple baselines, and we show its utility at predicting plausible futures of static images. Moreover, experiments and visualizations show the model internally learns useful features for recognizing actions with minimal supervision, suggesting scene dynamics are a promising signal for representation learning. We believe generative video models can impact many applications in video understanding and simulation.

Links