Synchronizing virtual backgrounds with monocular camera motion: A novel panoramic framework for video conferencing

点击次数:

DOI码:10.1016/j.vrih.2026.01.003

所属单位:University of Science and Technology Beijing

发表刊物:Virtual Reality & Intelligent Hardware

项目来源:NSFC (62402281, 62361146854); FRF-TP-25-036; Tsinghua-Tencent Joint Laboratory

关键字:Video processing; Multimedia; Human-computer interaction

摘要:We present a novel 360° panoramic video conferencing system that dynamically synchronizes virtual backgrounds with real-time camera motion, addressing the limitations of static backgrounds in conventional systems. By integrating robust human segmentation, monocular visual odometry (VO), and virtual environment rendering, our method achieves seamless alignment between foreground participants and immersive 3D virtual scenes. Unlike prior approaches that suffer from foreground-background desynchronization during camera rotations or user movements, our framework estimates camera rotation in 3-DoF using a hybrid pipeline combining feature-based patch tracking and pose smoothing, while ignoring translation artifacts to maintain stability. This work bridges the gap between computational efficiency and MR-driven telepresence, offering a practical solution for next-generation virtual collaboration.

备注:Funding: National Natural Science Foundation of China (62402281); National Natural Science Foundation of China (62361146854); Fundamental Research Funds for the Central Universities (FRF-TP-25-036); Tsinghua-Tencent Joint Laboratory for Internet Innovation Technology

合写作者:Zian Zhou,Fanglue Zhang,Song-Hai Zhang

第一作者:Sen-Zhe Xu

论文类型:期刊论文

学科门类:工学

文献类型:J

卷号:8

期号:2

页面范围:219–234

ISSN号:2096-5796

是否译文:

发布期刊链接:https://linkinghub.elsevier.com/retrieve/pii/S2096579626000033