Skip to main content
main-content

Tipp

Weitere Artikel dieser Ausgabe durch Wischen aufrufen

24.04.2020 | Ausgabe 5/2020 Open Access

International Journal of Computer Vision 5/2020

DGPose: Deep Generative Models for Human Body Analysis

Zeitschrift:
International Journal of Computer Vision > Ausgabe 5/2020
Autoren:
Rodrigo de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan, Ondrej Miksik, Adnane Boukhayma, N. Siddharth, Philip Torr
Wichtige Hinweise
Communicated by Xavier Alameda-Pineda, Elisa Ricci, Albert Ali Salah, Nicu Sebe, Shuicheng Yan.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Abstract

Deep generative modelling for human body analysis is an emerging problem with many interesting applications. However, the latent space learned by such approaches is typically not interpretable, resulting in less flexibility. In this work, we present deep generative models for human body analysis in which the body pose and the visual appearance are disentangled. Such a disentanglement allows independent manipulation of pose and appearance, and hence enables applications such as pose-transfer without specific training for such a task. Our proposed models, the Conditional-DGPose and the Semi-DGPose, have different characteristics. In the first, body pose labels are taken as conditioners, from a fully-supervised training set. In the second, our structured semi-supervised approach allows for pose estimation to be performed by the model itself and relaxes the need for labelled data. Therefore, the Semi-DGPose aims for the joint understanding and generation of people in images. It is not only capable of mapping images to interpretable latent representations but also able to map these representations back to the image space. We compare our models with relevant baselines, the ClothNet-Body and the Pose Guided Person Generation networks, demonstrating their merits on the Human3.6M, ChictopiaPlus and DeepFashion benchmarks.

Unsere Produktempfehlungen

Premium-Abo der Gesellschaft für Informatik

Sie erhalten uneingeschränkten Vollzugriff auf alle acht Fachgebiete von Springer Professional und damit auf über 45.000 Fachbücher und ca. 300 Fachzeitschriften.

Literatur
Über diesen Artikel

Weitere Artikel der Ausgabe 5/2020

International Journal of Computer Vision 5/2020 Zur Ausgabe

Premium Partner

    Bildnachweise