Square Superpixel Generation and Representation Learning via Granular Ball Computing

ArXi:2603.29460v1 Announce Type: new Superpixels provide a compact region-based representation that preserves object boundaries and local structures, and have. therefore. been widely used in a variety of vision tasks to reduce computational cost. However, most existing superpixel algorithms produce irregularly shaped regions, which are not well aligned with regular operators such as convolutions. Consequently, superpixels are often treated as an offline preprocessing step, limiting parallel implementation and hindering end-to-end optimization within deep learning pipelines.