Fine-structured object segmentation via neighborhood propagation

Yongchao Gong, Shiming Xiang, Chunhong Pan

Abstract: Highlights•We propose a method for fine-structured object segmentation via label propagation.•A novel affinity graph combining local and nonlocal connections is constructed.•We incorporate appearance models as labeling preference for the label propagation.•The energy minimization is achieved with a globally optimal closed-form solution.•Extensive experimental results demonstrate the effectiveness of our method.