In this work, we introduce the new scene understanding task of Part-aware Panoptic Segmentation (PPS), which aims to understand a scene at multiple levels of abstraction, and unifies the tasks of scene parsing and part parsing. For this novel task, we provide consistent annotations on two commonly used datasets: Cityscapes and Pascal VOC. Moreover, we present a single metric to evaluate PPS, called Part-aware Panoptic Quality (PartPQ). For this new task, using the metric and annotations, we set multiple baselines by merging results of existing state-of-the-art methods for panoptic segmentation and part segmentation. Finally, we conduct several experiments that evaluate the importance of the different levels of abstraction in this single task.
@article{arxiv.2106.06351,
title = {Part-aware Panoptic Segmentation},
author = {Daan de Geus and Panagiotis Meletis and Chenyang Lu and Xiaoxiao Wen and Gijs Dubbelman},
journal= {arXiv preprint arXiv:2106.06351},
year = {2021}
}
Comments
CVPR 2021. Code and data: https://github.com/tue-mps/panoptic_parts