Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2018

Abstract

Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information. In this work, we aim at generating such images based on a novel, two-stage reconstruction pipeline that learns a disentangled representation of the aforementioned image factors and generates novel person images at the same time. First, a multi-branched reconstruction network is proposed to disentangle and encode the three factors into embedding features, which are then combined to re-compose the input image itself. Second, three corresponding mapping functions are learned in an adversarial manner in order to map Gaussian noise to the learned embedding feature space, for each factor, respectively. Using the proposed framework, we can manipulate the foreground, background and pose of the input image, and also sample new embedding features to generate such targeted manipulations, that provide more control over the generation process. Experiments on the Market-1501 and Deepfashion datasets show that our model does not only generate realistic person images with new foregrounds, backgrounds and poses, but also manipulates the generated factors and interpolates the in-between states. Another set of experiments on Market-1501 shows that our model can also be beneficial for the person re-identification task.

Keywords

Image generation, generative adversarial networks, pose estimation, person re-identification

Discipline

Artificial Intelligence and Robotics | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR): Salt Lake City, June 18-22: Proceedings

First Page

99

Last Page

108

ISBN

9781538664209

Identifier

10.1109/CVPR.2018.00018

Publisher

IEEE Computer Society

City or Country

Los Alamitos, CA

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/CVPR.2018.00018

Download

Share

COinS