Alex Andonian, Sabrina Osmany, Audrey Cui, YeonHwan Park, Ali Jahanian...
TL;DR本研究探讨零样本语义图像绘画的问题。我们提出了一种新的方法,利用实际的文字描述,在合成图像中添加新的语义概念,通过结合最先进的逼真图像生成模型和文本 - 图像语义相似度网络,使用非梯度方法探索潜在空间,通过放松 GAN 的计算来针对特定区域的变化并进行用户研究进行比较。
Abstract
We investigate the problem of zero-shot semantic image painting. Instead of
painting modifications into an image using only concrete colors or a finite set
of semantic concepts, we ask how to create semantic paint based on open
full-text descriptions: our goal is to be able to point to