Higher-Order Minimum Cost Lifted Multicuts for Motion Segmentation
Higher-Order Minimum Cost Lifted Multicuts for Motion Segmentation
复制标题
DOI：
10.1109/iccv.2017.455
复制
发表时间：
2017-04
期刊：
影响因子：
--
通讯作者：
M. Keuper
中科院分区：
文献类型：
--
作者：
M. Keuper
大多数最先进的运动分割算法都是从图形模型中根据成对电位对局部实体（如点轨迹）的运动差异建模中提取潜力的。在这样的图上定义的最小代价多切割问题实例中的推理允许优化结果段的数量以及段分配。然而，两两电位限制了所采用的运动模型对平移差异的判别能力。更复杂的模型，如欧几里得变换或仿射变换，需要高阶势和由此产生的高阶图形模型中的可处理推理。在本文中，我们(1)将最小代价提升多切问题推广到超图，(2)提出了一个简单的原始可行启发式，允许在运动分割的点轨迹超图上定义的高阶提升多切问题实例实例中进行合理有效的推理。由此产生的运动分割比FBMS-59数据集上的最先进的运动分割更好。
Most state-of-the-art motion segmentation algorithms draw their potential from modeling motion differences of local entities such as point trajectories in terms of pairwise potentials in graphical models. Inference in instances of minimum cost multicut problems defined on such graphs allows to optimize the number of the resulting segments along with the segment assignment. However, pairwise potentials limit the discriminative power of the employed motion models to translational differences. More complex models such as Euclidean or affine transformations call for higher-order potentials and a tractable inference in the resulting higher-order graphical models. In this paper, we (1) introduce a generalization of the minimum cost lifted multicut problem to hypergraphs, and (2) propose a simple primal feasible heuristic that allows for a reasonably efficient inference in instances of higher-order lifted multicut problem instances defined on point trajectory hypergraphs for motion segmentation. The resulting motion segmentations improve over the state-of-the-art on the FBMS-59 dataset.