Abstract

Recently, a number of cross bilateral filtering methods have been proposed for solving multi-label problems in computer vision, such as stereo, optical flow and ob ject class segmentation that show an or- der of magnitude improvement in speed over previous methods. These methods have achieved good results despite using models with only unary and/or pairwise terms. However, previous work has shown the value of using models with higher-order terms e.g. to represent label consistency over large regions, or global co-occurrence relations. We show how these higher-order terms can be formulated such that filter-based inference re- mains possible. We demonstrate our techniques on joint stereo and ob ject labeling problems, as well as ob ject class segmentation, showing in addi- tion for joint ob ject-stereo labeling how our method provides an efficient approach to inference in product label-spaces. We show that we are able to speed up inference in these models around 10-30 times with respect to competing graph-cut/move-making methods, as well as maintaining or improving accuracy in all cases. We show results on PascalVOC-10 for ob ject class segmentation, and Leuven for joint ob ject-stereo labeling.