UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

GAN Inversion: A Survey

Xia, Weihao; Zhang, Yulun; Yang, Yujiu; Xue, Jing-Hao; Zhou, Bolei; Yang, Ming-Hsuan; (2022) GAN Inversion: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 10.1109/tpami.2022.3181070. Green open access

[thumbnail of 2101.05278v5.pdf]
2101.05278v5.pdf - Accepted Version

Download (1MB) | Preview


GAN inversion aims to invert a given image back into the latent space of a pretrained GAN model, for the image to be faithfully reconstructed from the inverted code by the generator. As an emerging technique to bridge the real and fake image domains, GAN inversion plays an essential role in enabling the pretrained GAN models such as StyleGAN and BigGAN to be used for real image editing applications. Meanwhile, GAN inversion also provides insights on the interpretation of GAN's latent space and how the realistic images can be generated. In this paper, we provide an overview of GAN inversion with a focus on its recent algorithms and applications. We cover important techniques of GAN inversion and their applications to image restoration and image manipulation. We further elaborate on some trends and challenges for future directions.

Type: Article
Title: GAN Inversion: A Survey
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/tpami.2022.3181070
Publisher version: https://doi.org/10.1109/TPAMI.2022.3181070
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Generative adversarial networks, interpretable machine learning, image reconstruction, image manipulation
UCL classification: UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
UCL > Provost and Vice Provost Offices > UCL BEAMS
URI: https://discovery.ucl.ac.uk/id/eprint/10150104
Downloads since deposit
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item