Multiple HD Screen-Based Virtual Studio System with Learned Mask-Free Portrait Harmonization

Author:

Jiang Jimao1ORCID,Lin Jiaxin1ORCID,Su Yuntao1ORCID,Fang Li12ORCID,Ye Long12

Affiliation:

1. School of Data Science and Media Intelligence, Communication University of China, Beijing 100024, China

2. Key Laboratory of Media Audio & Video (Communication University of China), Ministry of Education, Beijing 100024, China

Abstract

Virtual studio technology allows producers to combine live-action footage and computer-generated imagery and has promoted the development of film and television industry. However, the existing green screen-based virtual studio limits the visual effects just in postproduction. In this paper, we propose a new virtual studio system based on the recent emerging technology using multiple high-definition (HD) screens. Besides using traditional computer graphics like other similar systems, our system enables to capture panoramic video from the real world as the background and project it onto multiple HD screens, so as to recreate the scene in the studio. In addition, we propose a mask-free portrait harmonization network to make sure that the appearances of the foreground region and the background are consistent. Our portrait harmonization network does not need any auxiliary foreground mask and works in an end-to-end manner, which meets the postprocessing requirements for our virtual studio. Experimental result on real composite images shows that our network is superior to the state-of-the-art image harmonization method under the task of portrait harmonization. We also demonstrate our system with a CAVE system.

Funder

Fundamental Research Funds for the Central Universities

Publisher

Hindawi Limited

Subject

Electrical and Electronic Engineering,Computer Networks and Communications,Information Systems

Reference21 articles.

1. Region-aware Adaptive Instance Normalization for Image Harmonization

2. Virtual studios|Brainstorm Index

3. CJP Broadcast Index

4. Absen Virtual Studio LED Solutions Index

5. Insider

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3