Abstract
While GANs can produce photo-realistic images in ideal conditions for certain domains, the generation of full-body human images remains difficult due to the diversity of identities, hairstyles, clothing, and the variance in pose. In-stead of modeling this complex domain with a single GAN, we propose a novel method to combine multiple pretrained GANs, where one GAN generates a global canvas (e.g., human body) and a set of specialized GANs, or insets, focus on different parts (e.g., faces, shoes) that can be seamlessly inserted onto the global canvas. We model the problem as jointly exploring the respective latent spaces such that the generated images can be combined, by inserting the parts from the specialized generators onto the global canvas, without introducing seams. We demonstrate the setup by combining a full body GAN with a dedicated high-quality face GAN to produce plausible-looking humans. We evalu-ate our results with quantitative metrics and user studies.
Original language | English (US) |
---|---|
Title of host publication | Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 |
Publisher | IEEE Computer Society |
Pages | 7713-7722 |
Number of pages | 10 |
ISBN (Electronic) | 9781665469463 |
DOIs | |
State | Published - 2022 |
Event | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 - New Orleans, United States Duration: Jun 19 2022 → Jun 24 2022 |
Publication series
Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
---|---|
Volume | 2022-June |
ISSN (Print) | 1063-6919 |
Conference
Conference | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 |
---|---|
Country/Territory | United States |
City | New Orleans |
Period | 06/19/22 → 06/24/22 |
Bibliographical note
Publisher Copyright:© 2022 IEEE.
Keywords
- Image and video synthesis and generation
- Machine learning
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition