Image Co-skeletonization via Co-segmentation
This addresses the challenge of object skeletonization in natural images by leveraging commonness across images, but it is incremental as it builds on joint processing ideas like co-segmentation.
The paper tackles the problem of joint skeleton extraction from multiple images, a new topic called image co-skeletonization, by proposing a coupled framework with co-segmentation, and it achieves promising results across weakly-supervised, supervised, and unsupervised scenarios, as demonstrated on a new benchmark dataset of nearly 1.8k images.
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.