Unsupervised Domain Adaptation GAN Inversion for Image Editing

by   Siyu Xing, et al.

Existing GAN inversion methods work brilliantly for high-quality image reconstruction and editing while struggling with finding the corresponding high-quality images for low-quality inputs. Therefore, recent works are directed toward leveraging the supervision of paired high-quality and low-quality images for inversion. However, these methods are infeasible in real-world scenarios and further hinder performance improvement. In this paper, we resolve this problem by introducing Unsupervised Domain Adaptation (UDA) into the Inversion process, namely UDA-Inversion, for both high-quality and low-quality image inversion and editing. Particularly, UDA-Inversion first regards the high-quality and low-quality images as the source domain and unlabeled target domain, respectively. Then, a discrepancy function is presented to measure the difference between two domains, after which we minimize the source error and the discrepancy between the distributions of two domains in the latent space to obtain accurate latent codes for low-quality images. Without direct supervision, constructive representations of high-quality images can be spontaneously learned and transformed into low-quality images based on unsupervised domain adaptation. Experimental results indicate that UDA-inversion is the first that achieves a comparable level of performance with supervised methods in low-quality images across multiple domain datasets. We hope this work provides a unique inspiration for latent embedding distributions in image process tasks.


page 1

page 2

page 4

page 6

page 8

page 9


ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing

The StyleGAN family succeed in high-fidelity image generation and allow ...

Revisiting Latent Space of GAN Inversion for Real Image Editing

The exploration of the latent space in StyleGANs and GAN inversion exemp...

3DAvatarGAN: Bridging Domains for Personalized Editable Avatars

Modern 3D-GANs synthesize geometry and texture by training on large-scal...

From Continuity to Editability: Inverting GANs with Consecutive Images

Existing GAN inversion methods are stuck in a paradox that the inverted ...

Unsupervised Enhancement of Real-World Depth Images Using Tri-Cycle GAN

Low quality depth poses a considerable challenge to computer vision algo...

Improved StyleGAN Embedding: Where are the Good Latents?

StyleGAN is able to produce photorealistic images that are almost indist...

Please sign up or login with your details

Forgot password? Click here to reset