Semantic Image Manipulation Using Scene Graphs
Semantic Image Manipulation Using Scene Graphs
复制标题
DOI：
10.1109/cvpr42600.2020.00526
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Helisa Dhamo;Azade Farshad;Iro Laina;N. Navab;Gregory Hager;Federico Tombari;C. Rupprecht
中科院分区：
文献类型：
--
作者：
Helisa Dhamo;Azade Farshad;Iro Laina;N. Navab;Gregory Hager;Federico Tombari;C. Rupprecht
图像处理可以被认为是图像生成的特例，其中要产生的图像是对现有图像的修改。在很大程度上，图像生成和处理一直是对原始像素进行操作的任务。然而，在学习丰富的图像和对象表示方面的显著进展为主要由语义驱动的任务(如文本到图像或布局到图像的生成)开辟了道路。在我们的工作中，我们解决了从场景图处理图像的新问题，在该问题中，用户只需对从图像生成的语义图的节点或边进行更改即可编辑图像。我们的目标是对给定星座中的图像信息进行编码，并在此基础上生成新的星座，例如替换对象甚至改变对象之间的关系，同时尊重原始图像的语义和样式。我们介绍了一种空间语义场景图网络，它不需要对星座变化或图像编辑进行直接监督。这使得从现有的真实数据集训练系统成为可能，而不需要额外的注释工作。
Image manipulation can be considered a special case of image generation where the image to be produced is a modification of an existing image. Image generation and manipulation have been, for the most part, tasks that operate on raw pixels. However, the remarkable progress in learning rich image and object representations has opened the way for tasks such as text-to-image or layout-to-image generation that are mainly driven by semantics. In our work, we address the novel problem of image manipulation from scene graphs, in which a user can edit images by merely applying changes in the nodes or edges of a semantic graph that is generated from the image. Our goal is to encode image information in a given constellation and from there on generate new constellations, such as replacing objects or even changing relationships between objects, while respecting the semantics and style from the original image. We introduce a spatio-semantic scene graph network that does not require direct supervision for constellation changes or image edits. This makes it possible to train the system from existing real-world datasets with no additional annotation effort.