论文标题
用于GAN反转和编辑的空间自适应多层选择
Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing
论文作者
论文摘要
现有的gan倒置和编辑方法适用于具有干净背景的对准物体，例如肖像和动物面孔，但通常会为带有复杂场景布局和物体遮挡的更困难的类别而苦苦挣扎，例如汽车，动物和室外图像。我们提出了一种新方法，以在gan的潜在空间（例如stylegan2）中反转和编辑复杂的图像。我们的关键思想是用一系列层的集合探索反转，从而将反转过程适应图像的难度。我们学会预测不同图像段的“可逆性”，并将每个段投影到潜在层。更容易的区域可以倒入发电机潜在空间中的较早层，而更具挑战性的区域可以倒入更晚的特征空间。实验表明，与最新的复杂类别的方法相比，我们的方法获得了更好的反转结果，同时保持下游的编辑性。请参阅我们的项目页面，网址为https://www.cs.cmu.edu/~saminversion。
Existing GAN inversion and editing methods work well for aligned objects with a clean background, such as portraits and animal faces, but often struggle for more difficult categories with complex scene layouts and object occlusions, such as cars, animals, and outdoor images. We propose a new method to invert and edit such complex images in the latent space of GANs, such as StyleGAN2. Our key idea is to explore inversion with a collection of layers, spatially adapting the inversion process to the difficulty of the image. We learn to predict the "invertibility" of different image segments and project each segment into a latent layer. Easier regions can be inverted into an earlier layer in the generator's latent space, while more challenging regions can be inverted into a later feature space. Experiments show that our method obtains better inversion results compared to the recent approaches on complex categories, while maintaining downstream editability. Please refer to our project page at https://www.cs.cmu.edu/~SAMInversion.
