期刊
INTERNATIONAL JOURNAL OF COMPUTER VISION
卷 129, 期 1, 页码 -出版社
SPRINGER
DOI: 10.1007/s11263-020-01367-2
关键词
Dynamic 4D reconstruction; Segmentation; Reconstruction; 3D; Temporal coherence; Dynamic scenes
资金
- Royal Academy of Engineering Research Fellowship [RF-201718-17177]
- EPSRC Platform Grant on Audio-Visual Media Research [EP/P022529]
- EPSRC [EP/P022529/1, EP/M028321/1] Funding Source: UKRI
This paper introduces a general approach for obtaining a 4D representation of complex dynamic scenes from multi-view wide-baseline static or moving cameras without prior knowledge of the scene structure, appearance, or illumination. The contributions include automatic initial reconstruction, temporal coherence integration, and shape constraint, leading to improved accuracy in multi-view segmentation and dense reconstruction.
Existing techniques for dynamic scene reconstruction from multiple wide-baseline cameras primarily focus on reconstruction in controlled environments, with fixed calibrated cameras and strong prior constraints. This paper introduces a general approach to obtain a 4D representation of complex dynamic scenes from multi-view wide-baseline static or moving cameras without prior knowledge of the scene structure, appearance, or illumination. Contributions of the work are: an automatic method for initial coarse reconstruction to initialize joint estimation; sparse-to-dense temporal correspondence integrated with joint multi-view segmentation and reconstruction to introduce temporal coherence; and a general robust approach for joint segmentation refinement and dense reconstruction of dynamic scenes by introducing shape constraint. Comparison with state-of-the-art approaches on a variety of complex indoor and outdoor scenes, demonstrates improved accuracy in both multi-view segmentation and dense reconstruction. This paper demonstrates unsupervised reconstruction of complete temporally coherent 4D scene models with improved non-rigid object segmentation and shape reconstruction and its application to various applications such as free-view rendering and virtual reality.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据