Efficient Multiscale Object-based Superpixel Framework
This work addresses the need for efficient and effective object-based superpixel segmentation in computer vision applications, offering a novel approach that reduces computational time while enhancing delineation.
The authors tackled the problem of superpixel segmentation by proposing SICLE, a framework that incorporates object information to improve delineation and efficiency, achieving superior performance in multiple metrics compared to state-of-the-art methods.
Superpixel segmentation can be used as an intermediary step in many applications, often to improve object delineation and reduce computer workload. However, classical methods do not incorporate information about the desired object. Deep-learning-based approaches consider object information, but their delineation performance depends on data annotation. Additionally, the computational time of object-based methods is usually much higher than desired. In this work, we propose a novel superpixel framework, named Superpixels through Iterative CLEarcutting (SICLE), which exploits object information being able to generate a multiscale segmentation on-the-fly. SICLE starts off from seed oversampling and repeats optimal connectivity-based superpixel delineation and object-based seed removal until a desired number of superpixels is reached. It generalizes recent superpixel methods, surpassing them and other state-of-the-art approaches in efficiency and effectiveness according to multiple delineation metrics.