loading
Documents

Research.Publish.Connect.

Affiliation

Department of Computer Science, Technical University of Kaiserslautern, Kaiserslautern, Germany, Augmented Vision, German Research Center for Artificial Intelligence, Kaiserslautern, Germany
Context (please use complete words only)
Field
Sort by

1 Papers

Generation of Human Images with Clothing using Advanced Conditional Generative Adversarial Networks

Topics: Generative Adversarial Networks (GAN); Autoencoders; Learning Deep Generative Models; Human Pose Estimation

Authors: Sheela Kurupathi 1 , Pramod Murthy 2 and Didier Stricker 1

Affiliations: 1 Department of Computer Science, Technical University of Kaiserslautern, Kaiserslautern, Germany, Augmented Vision, German Research Center for Artificial Intelligence, Kaiserslautern, Germany , 2 Augmented Vision, German Research Center for Artificial Intelligence, Kaiserslautern, Germany

Digital Object Identifier: 10.5220/0009832200300041

Proceedings of DeLTA 2020, ISBN: 978-989-758-441-1

Collapse Button Quick Abstract
One of the main challenges of human-image generation is generating a person along with pose and clothing details. However, it is still a difficult task due to challenging backgrounds and appearance variance. Recently, various deep learning models like Stacked Hourglass networks, Variational Auto Encoders (VAE), and Generative Adversarial Networks (GANs) have been used to solve this problem. However, still, they do not generalize well to the real-world human-image generation task qualitatively. The main goal is to use the Spectral Normalization (SN) technique for training GAN to synthesize the human-image along with the perfect pose and appearance details of the person. In this paper, we have investigated how Conditional GANs, along with Spectral Normalization (SN), could synthesize the new image of the target person given the image of the person and the target (novel) pose desired. The model uses 2D keypoints to represent human poses. We also use adversarial hinge loss and present an ablation study. The proposed model variants have generated promising results on both the Market-1501 and DeepFashion Datasets. We supported our claims by benchmarking the proposed model with recent state-of-the-art models. Finally, we show how the Spectral Normalization (SN) technique influences the process of human-image synthesis.

Topic(s):

Filter listed results, by

Author

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic