DRSM: EFFICIENT NEURAL 4D DECOMPOSITION FOR DYNAMIC RECONSTRUCTION IN STATIONARY MONOCULAR CAMERAS

doi:10.1109/ICASSP48485.2024.10447270

科研成果详情

题名	DRSM: EFFICIENT NEURAL 4D DECOMPOSITION FOR DYNAMIC RECONSTRUCTION IN STATIONARY MONOCULAR CAMERAS
作者	Xie，Weixing 1,2,3; Dong，Xiao 4; Yang，Yong 1; Lin，Qiqin 1; Chen，Jingze 1; Yao，Junfeng 1,2,3; Guo，Xiaohu 5
发表日期	2024
会议名称	2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
会议录名称	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN	1520-6149
页码	3760-3764
会议日期	2024-04-14——2024-04-19
会议地点	Seoul
摘要	With the popularity of monocular videos generated by video sharing and live broadcasting applications, reconstructing and editing dynamic scenes in stationary monocular cameras has become a special but anticipated technology. In contrast to scene reconstructions that exploit multi-view observations, the problem of modeling a dynamic scene from a single view is significantly more under-constrained and ill-posed. Inspired by recent progress in neural rendering, we present a novel framework to tackle 4D decomposition problem for dynamic scenes in monocular cameras. Our framework utilizes decomposed static and dynamic feature planes to represent 4D scenes and emphasizes the learning of dynamic regions through dense ray casting. Inadequate 3D clues from a single-view and occlusion are also particular challenges in scene reconstruction. To overcome these difficulties, we propose deep supervised optimization and ray casting strategies. With experiments on various videos, our method generates higher-fidelity results than existing methods for single-view dynamic scene representation.
关键词	Dynamic Scene Reconstruction Neural Radiance Field Single-view Reconstruction
DOI	10.1109/ICASSP48485.2024.10447270
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-85195423078
引用统计
文献类型	会议论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/13846
专题	北师香港浸会大学
通讯作者	Yao，Junfeng
作者单位	1.Center for Digital Media Computing,School of Film,School of Informatics,Xiamen University,China 2.National Institute for Data Science in Health and Medicine,Xiamen University,China 3.Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan,Ministry of Culture and Tourism,China 4.Department of Computer Science,BNU-HKBU United International College,China 5.Department of Computer Science,TheUniversity of Texas,Dallas,United States
推荐引用方式 GB/T 7714	Xie，Weixing,Dong，Xiao,Yang，Yonget al. DRSM: EFFICIENT NEURAL 4D DECOMPOSITION FOR DYNAMIC RECONSTRUCTION IN STATIONARY MONOCULAR CAMERAS[C], 2024: 3760-3764.