main.pdf (34.48 MB)
Download file

The GAN that warped: semantic attribute editing with unpaired data

Download (34.48 MB)
conference contribution
posted on 2023-06-09, 20:47 authored by Garoe Dorta, Sara Vicente, Neill D F Campbell, Ivor SimpsonIvor Simpson
Deep neural networks have recently been used to edit images with great success, in particular for faces. However, they are often limited to only being able to work at a restricted range of resolutions. Many methods are so flexible that face edits can often result in an unwanted loss of identity. This work proposes to learn how to perform semantic image edits through the application of smooth warp fields. Previous approaches that attempted to use warping for semantic edits required paired data, i.e. example images of the same subject with different semantic attributes. In contrast, we employ recent advances in Generative Adversarial Networks that allow our model to be trained with unpaired data. We demonstrate face editing at very high resolutions (4k images) with a single forward pass of a deep network at a lower resolution. We also show that our edits are substantially better at preserving the subject's identity. The robustness of our approach is demonstrated by showing plausible image editing results on the Cub200 birds dataset. To our knowledge this has not been previously accomplished, due the challenging nature of the dataset.


Publication status

  • Published

File Version

  • Accepted version


2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)




IEEE Xplore

Event name

Computer Vision and Pattern Recognition (CVPR) 2020

Event location

Seattle, USA

Event type


Event date

16 - 20 June, 2020



Department affiliated with

  • Informatics Publications


© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date


First Open Access (FOA) Date


First Compliant Deposit (FCD) Date


Usage metrics

    University of Sussex (Publications)


    No categories selected