Narek Tumanyan, Omer Bar-Tal, Shai Bagon, Tali Dekel
TL;DR本文介绍了一种名为 Splice 的方法,通过集成 ViT 模型的语义信息,将一个自然图像中的物体的视觉外观转移到另一个图像中,该方法不需要使用对抗训练,也不需要任何额外的输入信息。
Abstract
We present a method for semantically transferring the visual appearance of
one natural image to another. Specifically, our goal is to generate an image in
which objects in a source structure image are "painted" with the visual
appearance of their semantically related objects in a targe