Consistent segment-wise matching with multi-layer graphs

Abstract

Segment-wise matching is an important research problem that supports higher-level understanding of shapes in geometry processing. Many existing segment-wise matching techniques assume perfect input segmentation, and would suffer from imperfect or over-segmented input. To handle this shortcoming, we propose multi-layer graphs (MLGs) to represent possible arrangements of partially merged segments of input shapes. We then adapt the diffusion pruning technique on the MLGs to find consistent segment-wise matching. To obtain high quality matching, we develop a voting step to find hierarchically consistent correspondences as final output. We evaluate our technique with both qualitative and quantitative experiments on both manmade and deformable shapes. Experimental results demonstrate the effectiveness of our technique when compared to two state-of-the-art methods.