Cross Anisotropic Cost Volume Filtering for Segmentation

Abstract

Abstract. We study an advanced method for supervised multi-label image segmentation. To this end, we adopt a classic framework which recently has been revitalised by Rhemann et al. (2011). Instead of the usual global energy minimisation step, it relies on a mere evaluation of a cost function for every solution label, which is followed by a spatial smoothing step of these costs. While Rhemann et al. concentrate on efficiency, the goal of this paper is to equip the general framework with sophisticated subcomponents in order to develop a high-quality method for multi-label image segmentation: First, we present a substantially improved cost computation scheme which incorporates texture descriptors, as well as an automatic feature selection strategy. This leads to a highdimensional feature space, from which we extract the label costs using a support vector machine. Second, we present a novel anisotropic diffusion scheme for the filtering step. In this PDE-based process, the smoothing of the cost volume is steered along the structures of the previously computed feature space. Experiments on widely used image databases show that our scheme produces segmentations of clearly superior quality.

Efficiency-enhanced cost-volume filtering featuring coarse-to-fine strategy

“…However, as mentioned in Section 1, the cost-volume filtering technique is not only used for them but also applied to wide range of multi-labeling problems such as image segmentation [20], and depth-map up-sampling [12].…”

“…2 In some cases, the label space does not need to be normalized because the scale of a label does not depend on the image coordinate space. Examples include depth-map up-sampling [12] and image segmentation [20]. in L n−2 j (artifacts become more problematic as the scale difference increases).…”

“…Rhemann et al [28] presented a local approach called cost-volume filtering (CVF), which efficiently solves general multi-labeling problems by performing MRF optimization via fast local filtering of label costs instead of global smoothing. CVF is easy to implement and provides high-quality results; therefore, it has been widely used to solve various multi-labeling problems [10,12,18,20,40]. However, a limitation of CVF is that it does not scale to extremely large label sets (e.g., sub-pixel stereo matching and up-sampling of 16-bit depth maps captured by a Kinect sensor).…”

“…Note that we are not proposing a better algorithm for stereo matching and optical flow estimation, but proposing a coarse-to-fine method to drastically reduce the computational time of CVF while preserving its accuracy. As presented in [10,12,18,20,28], the CVF can be used for wide range of applications and the stereo matching and the optical flow estimation presented in this paper is just an example.…”

Coarse-to-fine strategy for efficient cost-volume filtering

“…The trick is that CVF substitutes the fast local filtering of label costs for the global smoothing in the MRF optimization. Since CVF is easy to implement yet provides high-quality results, it has been widely used to solve various multi-label problems [5,6,7,8,9]. However, a limitation of CVF is that it does not scale to the extremely large label set (e.g., sub-pixel stereo matching and upsampling of the 16-bit depth map from the kinect sensor).…”