Photo Stand-Out: Photography with Virtual Character
Yujia Wang1,* Sifan Hou1,* Bing Ning2, Wei Liang1
1Beijing Institute of Technology
2Beijing Institute of Fashion Technology
*Equal Contributors
Abstract
Extended augmented reality techniques and applications of virtual characters,
like taking photography with a female warrior in Sci-Fi museum, provide a diverse and immersive experience in the real world.
In different scenes, the virtual character should be posed naturally with the user,
expressing an aesthetic pose, to obtain photography with the personalized posed virtual character rather than that with the
immutable pre-designed pose.
In this paper, we propose a novel optimization framework to synthesize an aesthetic pose for the virtual character
with respect to the presented user's pose. Our approach applies aesthetic evaluation that exploits fully connected
neural networks trained on example images of real-word. The aesthetic pose of the virtual character is obtained by
optimizing a cost function that guides the rotation of each body joint angles. In our experiments, we demonstrate
the proposed approach can synthesize poses for virtual characters according to user pose inputs.
We also conducted quantitative and qualitative experiments of the synthesized results to validate the efficacy of our approach.
Keywords
Pose Synthesis, Pose Aesthetic Classifcation, Pose Optimization.
Publication
Photo Stand-Out: Photography with Virtual Character
Yujia Wang,
Sifan Hou,
Bing Ning,
Wei Liang
ACM Multimedia Conference (ACM MM 2020)
Paper
, Video
, Dataset (Coming Soon)
BibTex
@inproceedings{ps2020wang,
title=
{Photo Stand-Out: Photography with Virtual Character},
author = {Wang, Yujia and Sifan, Hou and Bing, Ning and Wei, Liang},
booktitle={ACM Multimedia},
volume = {38},
number = {6},
year = {2020}
}
- 媒体计算与智能系统实验室
- Media Computing and Intelligent Systems Lab
Beijing Institute of Technology Copyright Address: 5 South Zhongguancun
Street, Haidian District, Beijing Postcode: 100081