Third Time’s the Charm? Image and Video Editing with StyleGAN3
author
Yuval Alaluf
Link
论文地址
Code
StyleGAN is arguably one of the most intriguing and well-studied generative models, demonstrating impressive performance in image generation, inversion, and manipulation. In this work, we explore the recent StyleGAN3 architecture, compare it to its predecessor, and investigate its unique advantages, as well as drawbacks. In particular, we demonstrate that while StyleGAN3 can be trained on unaligned data, one can still use aligned data for training, without hindering the ability to generate unaligned imagery. Next, our analysis of the disentanglement of the different latent spaces of StyleGAN3 indicates that the commonly used W/W+ spaces are more entangled than their StyleGAN2 counterparts, underscoring the benefits of using the StyleSpace for fine-grained editing. Considering image inversion, we observe that existing encoder-based techniques struggle when trained on unaligned data. We therefore propose an encoding scheme trained solely on aligned data, yet can still invert unaligned images. Finally, we introduce a novel video inversion and editing workflow that leverages the capabilities of a fine-tuned StyleGAN3 generator to reduce texture sticking and expand the field of view of the edited video.
在mapping network部分,并无变化,通过全连接网络将初始latent code z ~N(0,1) [512] 转换成w,并加入可学习的latent space W。
与Stylegan2相比,Stylegan3的synthesis network由固定数量的卷积层构成,与输出图像分辨率无关。Stylegan2中的constant 4*4被傅里叶特征(Fourier feat)取代,其中四个参数(sin a , cos a , x , y)通过学习仿射层从w0获取。在剩下的层中,每个wi被送入一个独立的学习仿射层,产生的modulation factors用来调整卷积核权重。