Image Co-skeletonization via Co-segmentation

TL;DR

This paper introduces the novel task of image co-skeletonization, jointly extracting object skeletons across image collections, and proposes a coupled framework that leverages co-segmentation and skeletonization to improve results.

Contribution

It defines the new problem of image co-skeletonization, constructs a benchmark dataset, and develops a coupled framework for joint skeleton extraction and segmentation.

Findings

The method achieves promising results across different supervision scenarios.

A new benchmark dataset with 1.8k images across 38 categories was created.

Joint processing improves skeletonization and segmentation accuracy.

Abstract

Recent advances in the joint processing of images have certainly shown its advantages over individual processing. Different from the existing works geared towards co-segmentation or co-localization, in this paper, we explore a new joint processing topic: image co-skeletonization, which is defined as joint skeleton extraction of objects in an image collection. Object skeletonization in a single natural image is a challenging problem because there is hardly any prior knowledge about the object. Therefore, we resort to the idea of object co-skeletonization, hoping that the commonness prior that exists across the images may help, just as it does for other joint processing problems such as co-segmentation. We observe that the skeleton can provide good scribbles for segmentation, and skeletonization, in turn, needs good segmentation. Therefore, we propose a coupled framework for co-skeletonization and co-segmentation tasks so that they are well informed by each other, and benefit each other synergistically. Since it is a new problem, we also construct a benchmark dataset by annotating nearly 1.8k images spread across 38 categories. Extensive experiments demonstrate that the proposed method achieves promising results in all the three possible scenarios of joint-processing: weakly-supervised, supervised, and unsupervised.