A Graph Multi-separator Problem for Image Segmentation
This work addresses image segmentation for applications like analyzing foam cells and filaments, but it appears incremental as it builds on the closely related lifted multicut problem.
The authors tackled the image segmentation problem by formulating it as a novel combinatorial optimization problem called the multi-separator problem, which explicitly models segment separators, and they developed efficient algorithms for special cases and local search methods, demonstrating effectiveness on simulated volume images of foam cells and filaments.
We propose a novel abstraction of the image segmentation task in the form of a combinatorial optimization problem that we call the multi-separator problem. Feasible solutions indicate for every pixel whether it belongs to a segment or a segment separator, and indicate for pairs of pixels whether or not the pixels belong to the same segment. This is in contrast to the closely related lifted multicut problem where every pixel is associated to a segment and no pixel explicitly represents a separating structure. While the multi-separator problem is NP-hard, we identify two special cases for which it can be solved efficiently. Moreover, we define two local search algorithms for the general case and demonstrate their effectiveness in segmenting simulated volume images of foam cells and filaments.