A Simple Baseline for StyleGAN Inversion

by   Tianyi Wei, et al.

This paper studies the problem of StyleGAN inversion, which plays an essential role in enabling the pretrained StyleGAN to be used for real facial image editing tasks. This problem has the high demand for quality and efficiency. Existing optimization-based methods can produce high quality results, but the optimization often takes a long time. On the contrary, forward-based methods are usually faster but the quality of their results is inferior. In this paper, we present a new feed-forward network for StyleGAN inversion, with significant improvement in terms of efficiency and quality. In our inversion network, we introduce: 1) a shallower backbone with multiple efficient heads across scales; 2) multi-layer identity loss and multi-layer face parsing loss to the loss function; and 3) multi-stage refinement. Combining these designs together forms a simple and efficient baseline method which exploits all benefits of optimization-based and forward-based methods. Quantitative and qualitative results show that our method performs better than existing forward-based methods and comparably to state-of-the-art optimization-based methods, while maintaining the high efficiency as well as forward-based methods. Moreover, a number of real image editing applications demonstrate the efficacy of our method. Our project page is  <https://wty-ustc.github.io/inversion>.


page 1

page 6

page 7

page 8

page 12

page 13

page 14

page 15


Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models

In image editing employing diffusion models, it is crucial to preserve t...

PREIM3D: 3D Consistent Precise Image Attribute Editing from a Single Image

We study the 3D-aware image attribute editing problem in this paper, whi...

CoralStyleCLIP: Co-optimized Region and Layer Selection for Image Editing

Edit fidelity is a significant issue in open-world controllable generati...

Style Transformer for Image Inversion and Editing

Existing GAN inversion methods fail to provide latent codes for reliable...

Improved Image Matting via Real-time User Clicks and Uncertainty Estimation

Image matting is a fundamental and challenging problem in computer visio...

Improving Negative-Prompt Inversion via Proximal Guidance

DDIM inversion has revealed the remarkable potential of real image editi...

Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations

Existing techniques for model inversion typically rely on hard-to-tune r...

Please sign up or login with your details

Forgot password? Click here to reset