Abstract / Description of output
Deep generative modelling for human body analysis is an emerging problem with many interesting applications. However, the latent space learned by such models is typically not interpretable, resulting in less flexible models. In this work, we adopt a structured semi-supervised approach and present a deep generative model for human body analysis where the body pose and the visual appearance are disentangled in the latent space. Such a disentanglement allows independent manipulation of pose and appearance, and hence enables applications such as pose-transfer without being explicitly trained for such a task. In addition, our setting allows for semi-supervised pose estimation, relaxing the need for labelled data. We demonstrate the capabilities of our generative model on the Human3.6M and on the DeepFashion datasets.
Original language | English |
---|---|
Title of host publication | Computer Vision -- ECCV 2018 Workshops |
Editors | Laura Leal-Taixé, Stefan Roth |
Place of Publication | Cham |
Publisher | Springer |
Pages | 500-517 |
Number of pages | 18 |
ISBN (Electronic) | 978-3-030-11012-3 |
ISBN (Print) | 978-3-030-11011-6 |
DOIs | |
Publication status | Published - 29 Jan 2019 |
Event | 9th International Workshop on Human Behavior Understanding: Generating Visual Data of Human Behavior - Munich, Germany Duration: 9 Sept 2018 → 9 Sept 2018 http://xavirema.eu/HBUGEN2018/index.html |
Publication series
Name | Lecture Notes in Computer Science |
---|---|
Publisher | Springer, Cham |
Volume | 11130 |
ISSN (Print) | 0302-9743 |
ISSN (Electronic) | 1611-3349 |
Workshop
Workshop | 9th International Workshop on Human Behavior Understanding |
---|---|
Abbreviated title | HBUGEN 2018 |
Country/Territory | Germany |
City | Munich |
Period | 9/09/18 → 9/09/18 |
Internet address |
Keywords / Materials (for Non-textual outputs)
- Deep generative models
- Variational autoencoders
- Semi-supervised learning
- Human pose estimation
- Analysis-by-synthesis