Fast Guided Global Interpolation for Depth and Motion
Fast Guided Global Interpolation for Depth and Motion
复制标题
DOI：
10.1007/978-3-319-46487-9_44
复制
发表时间：
2016-10
期刊：
影响因子：
--
通讯作者：
Yu Li;Dongbo Min;M. Do;Jiangbo Lu
中科院分区：
文献类型：
--
作者：
Yu Li;Dongbo Min;M. Do;Jiangbo Lu
我们研究的问题上采样的低分辨率的深度图和插值的初始稀疏运动匹配，从相应的高分辨率彩色图像的指导。这两个任务的共同目标是通过2D引导插值过程将一组稀疏数据点（规则分布或分散）致密化为完整的图像网格。我们提出了一个统一的方法，铸造的基本指导插值问题到一个层次，全局优化框架。建立在加权最小二乘（WLS）公式与其最近的快速求解器-快速全局平滑（FGS）技术，我们的方法通过有效地执行级联，全局插值（或平滑）与交替的指导，逐步密集的输入数据集。我们的级联方案有效地解决了稀疏输入数据和引导图像之间的潜在结构不一致，同时保留深度或运动边界。为了防止低置信度的新数据点污染下一个插值过程，我们还谨慎地评估插值中间数据的一致性。实验表明，我们的一般插值方法成功地解决了几个臭名昭著的挑战。我们的方法在各种基准评估上实现了定量竞争结果，同时运行速度比专门为深度上采样或运动插值设计的其他竞争方法快得多。
We study the problems of upsampling a low-resolution depth map and interpolating an initial set of sparse motion matches, with the guidance from a corresponding high-resolution color image. The common objective for both tasks is to densify a set of sparse data points, either regularly distributed or scattered, to a full image grid through a 2D guided interpolation process. We propose a unified approach that casts the fundamental guided interpolation problem into a hierarchical, global optimization framework. Built on a weighted least squares (WLS) formulation with its recent fast solver – fast global smoothing (FGS) technique, our method progressively densifies the input data set by efficiently performing the cascaded, global interpolation (or smoothing) with alternating guidances. Our cascaded scheme effectively addresses the potential structure inconsistency between the sparse input data and the guidance image, while preserving depth or motion boundaries. To prevent new data points of low confidence from contaminating the next interpolation process, we also prudently evaluate the consensus of the interpolated intermediate data. Experiments show that our general interpolation approach successfully tackles several notorious challenges. Our method achieves quantitatively competitive results on various benchmark evaluations, while running much faster than other competing methods designed specifically for either depth upsampling or motion interpolation.