A Convex Relaxation Approach to Space Time Multi-view 3D Reconstruction
A Convex Relaxation Approach to Space Time Multi-view 3D Reconstruction
复制标题
时空多视图 3D 重建的凸弛豫方法
DOI：
--
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
D. Cremers
中科院分区：
文献类型：
--
作者：
Martin R. Oswald;D. Cremers
我们提出了一种凸松弛方法，从多个视频的时空3D重建。将Unger等人的工作推广。[16]，Kolev等人。[8]到4D设置，我们将随时间重建的问题转换为4D空间中的二进制标记问题。我们提出了一个变分公式相结合的照片一致性为基础的数据项与时空总变分正则化。特别是，我们提出了一个新的数据项，这是更快的计算和更好地适合宽基线相机设置时，照片的一致性措施是不可靠的或失踪。建议的功能可以使用凸松弛技术全局最小化。在各种公共可用数据集上的大量实验表明，我们可以计算详细的和时间上一致的重建。特别地，时间正则化允许减少体素随时间的抖动。
We propose a convex relaxation approach to space-time 3D reconstruction from multiple videos. Generalizing the works Unger et al. [16], Kolev et al. [8] to the 4D setting, we cast the problem of reconstruction over time as a binary labeling problem in a 4D space. We propose a variational formulation which combines a photo consistency based data term with a spatio-temporal total variation regularization. In particular, we propose a novel data term that is both faster to compute and better suited for wide-baseline camera setups when photo consistency measures are unreliable or missing. The proposed functional can be globally minimized using convex relaxation techniques. Numerous experiments on a variety of public ally available data sets demonstrate that we can compute detailed and temporally consistent reconstructions. In particular, the temporal regularization allows to reduce jittering of voxels over time.