BriefGPT.xyz
Aug, 2019
利用神经重新模拟生成单张图像中的反弹
Neural Re-Simulation for Generating Bounces in Single Images
HTML
PDF
Carlo Innamorati, Bryan Russell, Danny M. Kaufman, and Niloy J. Mitra
TL;DR
本文提出了一种使用神经网络生成虚拟物体与静止图像环境真实交互的视频的方法，该网络能够通过学习来纠正物理模拟的不完整和不准确信息，称之为神经再仿真过程，实验结果显示该方法可以在合成场景和现实图片中取得显著提高。
Abstract
We introduce a method to generate videos of dynamic
virtual objects
plausibly interacting via collisions with a still image's environment. Given a starting trajectory,
physically simulated
with the estimated geom
→