arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00740cs.CV
收藏

DRSM:用于固定单目相机动态重建的高效神经4D分解方法

DRSM: efficient neural 4d decomposition for dynamic reconstruction in stationary monocular cameras

Xiamen University(厦门大学);National Institute for Data Science in Health and Medicine, Xiamen University(厦门大学健康与医学数据科学国家研究所);BNU-HKBU United International College(北京师范大学-香港浸会大学联合国际学院);The University of Texas at Dallas(德克萨斯大学达拉斯分校)

Weixing Xie, Xiao Dong, Yong Yang, Qiqin Lin, Jingze Chen, Junfeng Yao, Xiaohu Guo

AI总结:

针对固定单目相机动态场景重建约束少、病态性强及3D线索不足、遮挡等问题,提出基于分解静动态特征平面与密集光线投射的DRSM框架,结合深度监督优化策略,实现更高保真的单视角4D动态场景重建。

摘要:

随着视频分享与直播应用生成的单目视频日益普及,对固定单目相机拍摄的动态场景进行重建与编辑已成为一项特殊但备受期待的技术。与利用多视角观测的场景重建方法相比,从单视角对动态场景建模的问题约束明显更少,且更具病态性。受神经渲染领域近期进展的启发,我们提出了一个全新框架,用于解决单目相机下动态场景的4D分解问题。该框架采用分解后的静态与动态特征平面对4D场景进行表征,并通过密集光线投射强化对动态区域的学习。单视角带来的3D线索不足以及遮挡问题,也是场景重建中的特殊挑战。为攻克这些难题,我们提出了深度监督优化与光线投射策略。在多类视频上开展的实验表明,相较于现有的单视角动态场景表征方法,我们的方法能生成保真度更高的结果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑