Real-time Gaussian Splatting for Dynamic Reconstruction in Stationary Monocular Cameras

doi:10.1109/SEAI62072.2024.10674501

科研成果详情

题名	Real-time Gaussian Splatting for Dynamic Reconstruction in Stationary Monocular Cameras
作者	Chen，Minyu 1; Xie，Weixing 2; Deng，Zhiyang 1; Shi，Chenglong 1; Gou，Ruoxuan 1; Chen，Yingxuan 1; Dong，Xiao 1
发表日期	2024
会议名称	4th IEEE International Conference on Software Engineering and Artificial Intelligence, SEAI 2024
会议录名称	2024 4th IEEE International Conference on Software Engineering and Artificial Intelligence, SEAI 2024
页码	33-37
会议日期	2024-06-21——2024-06-23
会议地点	Xiamen
摘要	With the development of differentiable rendering techniques such as Gaussian Splatting, the quality of 3D reconstruction has gradually improved. Nowadays on social platforms, the number of videos shot with fixed cameras increases significantly. However, current 3D reconstruction methods require multi-view observation as input, and perform poorly on single-view videos, such as reconstruction blur for moving objects. In order to solve the problem of dynamic scene reconstruction under a single perspective, we propose a network based on dynamic Gaussian Splatting and implement the task of removing objects during reconstruction process. Our method uses the depth projection to obtain a point cloud as the initialization of Gaussians, and designs a lightweight Gaussian deformation module to obtain the changes of each Gaussian over time. The deformation module utilizes discrete feature planes as encoder, which significantly reduces training time. In order to remove dynamic objects, we use an object mask and design a loss function to restore the color of occluded area. We conducted extensive experiments to evaluate our method and SOTA reconstruction methods. Our method not only significantly improves the reconstruction quality and training time, but also achieves real-time rendering.
关键词	3D Reconstruction Gaussian Splatting Real-time Rendering
DOI	10.1109/SEAI62072.2024.10674501
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-85205971468
引用统计
文献类型	会议论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/13847
专题	北师香港浸会大学
通讯作者	Dong，Xiao
作者单位	1.BNU-HKBU United International College,Guangdong Provincial Key Laboratory IRADS,Department of Computer Science,Zhuhai,519087,China 2.National Institute for Data Science in Health and Medicine,Xiamen University,China
第一作者单位	北师香港浸会大学
通讯作者单位	北师香港浸会大学
推荐引用方式 GB/T 7714	Chen，Minyu,Xie，Weixing,Deng，Zhiyanget al. Real-time Gaussian Splatting for Dynamic Reconstruction in Stationary Monocular Cameras[C], 2024: 33-37.