Abstract
We introduce a segmentation-guided approach to synthesise images that integrate features from two distinct domains. Images synthesised by our dual-domain model belong to one domain within the semantic-mask, and to another in the rest of the image - smoothly integrated. We build on the successes of few-shot StyleGAN and single-shot semantic segmentation to minimise the amount of training required in utilising two domains.The method combines few-shot cross-domain StyleGAN with a latent optimiser to achieve images containing features of two distinct domains. We use a segmentation-guided perceptual loss, which compares both pixel-level and activations between domain-specific and dual-domain synthetic images. Results demonstrate qualitatively and quantitatively that our model is capable of synthesising dual-domain images on a variety of objects (faces, horses, cats, cars), domains (natural, caricature, sketches) and part-based masks (eyes, nose, mouth, hair, car bonnet). The code is publicly available
Original language | English |
---|---|
Title of host publication | Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022 |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
Pages | 506-515 |
Number of pages | 10 |
ISBN (Electronic) | 978-1-6654-8739-9 |
ISBN (Print) | 978-1-6654-8740-5 |
DOIs | |
Publication status | Published - 23 Aug 2022 |
Publication series
Name | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
---|---|
Volume | 2022-June |
ISSN (Print) | 2160-7508 |
ISSN (Electronic) | 2160-7516 |
Bibliographical note
Publisher Copyright:© 2022 IEEE.