FDA-GAN: Flow-based Dual Attention GAN for Human Pose Transfer

Human pose transfer aims at transferring the appearance of the source person to the target pose. Existing methods utilizing flow-based warping for non-rigid human image generation have achieved great success. However, they fail to preserve the appearance details in synthesized images since the spati...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Ma, Liyuan, Huang, Kejie, Wei, Dongxu, Ming, Zhaoyan, Shen, Haibin
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 01.12.2021
Subjects
Deformation
Formability
Image processing
Occlusion
Online AccessGet full text

Cover

More Information
Summary:Human pose transfer aims at transferring the appearance of the source person to the target pose. Existing methods utilizing flow-based warping for non-rigid human image generation have achieved great success. However, they fail to preserve the appearance details in synthesized images since the spatial correlation between the source and target is not fully exploited. To this end, we propose the Flow-based Dual Attention GAN (FDA-GAN) to apply occlusion- and deformation-aware feature fusion for higher generation quality. Specifically, deformable local attention and flow similarity attention, constituting the dual attention mechanism, can derive the output features responsible for deformable- and occlusion-aware fusion, respectively. Besides, to maintain the pose and global position consistency in transferring, we design a pose normalization network for learning adaptive normalization from the target pose to the source person. Both qualitative and quantitative results show that our method outperforms state-of-the-art models in public iPER and DeepFashion datasets.
ISSN:2331-8422