Robust Region Detection via Consensus Segmentation of Deformable Shapes

ensemble of segmentations consensus segmentation Figure 1: The proposed framework allows to obtain robust surface segmentations in a principled way. Here, an initial ensemble of 50 segmentations (we show only 5 for visualization purposes) is generated via a clustering process on the Global Point Signature embedding of the shape. Given this ensemble, the corresponding consensus is defined as the unknown segmentation that is as close as possible to all the others. Note that the number of regions in the ensemble and in the final consensus segmentation are not necessarily the same. The detected regions are stable across non-rigid deformations of the shape. We consider the problem of stable region detection and segmentation of deformable shapes. We pursue this goal by determining a consensus segmentation from a heterogeneous ensemble of putative segmentations, which are generated by a clustering process on an intrinsic embedding of the shape. The intuition is that the consensus segmentation, which relies on aggregate statistics gathered from the segmentations in the ensemble, can reveal components in the shape that are more stable to deformations than the single baseline segmentations. Compared to the existing approaches, our solution exhibits higher robustness and repeatability throughout a wide spectrum of non-rigid transformations. It is computationally efficient, naturally extendible to point clouds, and remains semantically stable even across different object classes. A quantitative evaluation on standard datasets confirms the potentiality of our method as a valid tool for deformable shape analysis