Layered image motion with explicit occlusions, temporal consistency, and depth ordering
Layered image motion with explicit occlusions, temporal consistency, and depth ordering
复制标题
DOI：
--
复制
发表时间：
2010-12
期刊：
影响因子：
3.2
通讯作者：
Deqing Sun;Erik B. Sudderth;Michael J. Black
中科院分区：
文献类型：
--
作者：
Deqing Sun;Erik B. Sudderth;Michael J. Black
分层模型是描述包含可能相互重叠和遮挡的平滑表面的自然场景的强大方法。对于图像运动估计，这样的模型有很长的历史，但还没有实现非分层方法的广泛使用或准确性。我们提出了一个新的概率模型的光流层，解决了许多以前的方法的缺点。特别是，我们定义了一个概率图形模型，明确捕捉：1）闭塞和disocclusion; 2）层的深度排序; 3）层分割的时间一致性。此外，在每一层中的光流被建模的参数模型和基于MRF与鲁棒的空间先验的平滑偏差的组合;所得到的模型允许层中的粗糙度。最后，一个关键的贡献是制定的层使用图像相关的隐藏字段之前的基础上最近的静态场景分割模型。该方法在Middlebury基准测试中取得了最先进的结果，并产生了有意义的场景分割和检测到的遮挡区域。
Layered models are a powerful way of describing natural scenes containing smooth surfaces that may overlap and occlude each other. For image motion estimation, such models have a long history but have not achieved the wide use or accuracy of non-layered methods. We present a new probabilistic model of optical flow in layers that addresses many of the shortcomings of previous approaches. In particular, we define a probabilistic graphical model that explicitly captures: 1) occlusions and disocclusions; 2) depth ordering of the layers; 3) temporal consistency of the layer segmentation. Additionally the optical flow in each layer is modeled by a combination of a parametric model and a smooth deviation based on an MRF with a robust spatial prior; the resulting model allows roughness in layers. Finally, a key contribution is the formulation of the layers using an image-dependent hidden field prior based on recent models for static scene segmentation. The method achieves state-of-the-art results on the Middlebury benchmark and produces meaningful scene segmentations as well as detected occlusion regions.