Panoptic Segmentation
This work revives community interest in a unified approach to image segmentation, addressing a foundational problem in computer vision for real-world vision systems.
The authors introduced panoptic segmentation, a unified task combining semantic and instance segmentation to generate coherent scene segmentations, and proposed a novel panoptic quality metric to evaluate performance across all classes, revealing insights from studies on three datasets.
We propose and study a task we name panoptic segmentation (PS). Panoptic segmentation unifies the typically distinct tasks of semantic segmentation (assign a class label to each pixel) and instance segmentation (detect and segment each object instance). The proposed task requires generating a coherent scene segmentation that is rich and complete, an important step toward real-world vision systems. While early work in computer vision addressed related image/scene parsing tasks, these are not currently popular, possibly due to lack of appropriate metrics or associated recognition challenges. To address this, we propose a novel panoptic quality (PQ) metric that captures performance for all classes (stuff and things) in an interpretable and unified manner. Using the proposed metric, we perform a rigorous study of both human and machine performance for PS on three existing datasets, revealing interesting insights about the task. The aim of our work is to revive the interest of the community in a more unified view of image segmentation.