Supervised Attribute Information Removal and Reconstruction for Image Manipulation
Supervised Attribute Information Removal and Reconstruction for Image Manipulation
复制标题
DOI：
10.48550/arxiv.2207.06555
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Nannan Li;Bryan A. Plummer
中科院分区：
文献类型：
--
作者：
Nannan Li;Bryan A. Plummer
属性操作的目标是控制给定图像中的指定属性。先前的工作通过学习每个属性的解纠缠表示来解决这个问题，使其能够将编码的源属性操作为目标属性。然而，编码的属性通常与相关的图像内容相关。因此，源属性信息通常可以隐藏在解缠的特征中，导致不想要的图像编辑效果。在本文中，我们提出了一个属性信息删除和重建（AIRR）网络，防止这样的信息隐藏，通过学习如何完全删除属性信息，创建属性排除功能，然后学习直接注入重建图像中所需的属性。我们在四个不同的数据集上评估了我们的方法，这些数据集具有各种属性，包括DeepFashion Synthesis，DeepFashion Fine-grained Attribute，CelebA和CelebA-HQ，其中我们的模型将属性操作精度和top-k检索率平均提高了10%。一项用户研究还报告说，在高达76%的情况下，AIRR操作的图像比以前的工作更受欢迎。
The goal of attribute manipulation is to control specified attribute(s) in given images. Prior work approaches this problem by learning disentangled representations for each attribute that enables it to manipulate the encoded source attributes to the target attributes. However, encoded attributes are often correlated with relevant image content. Thus, the source attribute information can often be hidden in the disentangled features, leading to unwanted image editing effects. In this paper, we propose an Attribute Information Removal and Reconstruction (AIRR) network that prevents such information hiding by learning how to remove the attribute information entirely, creating attribute excluded features, and then learns to directly inject the desired attributes in a reconstructed image. We evaluate our approach on four diverse datasets with a variety of attributes including DeepFashion Synthesis, DeepFashion Fine-grained Attribute, CelebA and CelebA-HQ, where our model improves attribute manipulation accuracy and top-k retrieval rate by 10% on average over prior work. A user study also reports that AIRR manipulated images are preferred over prior work in up to 76% of cases.