Frühstück, A;
Singh, KK;
Shechtman, E;
Mitra, NJ;
Wonka, P;
Lu, J;
(2022)
InsetGAN for Full-Body Image Generation.
In:
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
(pp. pp. 7713-7722).
IEEE
Preview |
Text
Fruhstuck_InsetGAN_for_Full-Body_Image_Generation_CVPR_2022_paper.pdf - Published Version Download (10MB) | Preview |
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.
| Type: | Proceedings paper |
|---|---|
| Title: | InsetGAN for Full-Body Image Generation |
| Event: | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
| Dates: | 18 Jun 2022 - 24 Jun 2022 |
| ISBN-13: | 9781665469463 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/CVPR52688.2022.00757 |
| Publisher version: | https://doi.org/10.1109/CVPR52688.2022.00757 |
| 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: | Image and video synthesis and generation; Machine learning, Measurement, Solid modeling, Three-dimensional displays, Shape, Image synthesis, Transformers, Generators |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10160918 |
Loading...
Loading...Loading...| 1. |  United States | 8 |
| 2. |  United Kingdom | 4 |
| 3. |  France | 3 |
| 4. |  Germany | 3 |
| 5. |  Austria | 2 |
| 6. |  China | 2 |
| 7. |  India | 1 |
| 8. |  Poland | 1 |
| 9. |  Ukraine | 1 |
| 10. |  Chile | 1 |
Archive Staff Only
 |
View Item |
