Part-aware Panoptic Segmentation

Daan de Geus, Panagiotis Meletis, Chenyang Lu, Xiaoxiao Wen, Gijs Dubbelman

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

23 Citations (Scopus)
64 Downloads (Pure)


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.
Original languageEnglish
Title of host publication2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherInstitute of Electrical and Electronics Engineers
Number of pages10
ISBN (Electronic)978-1-6654-4509-2
Publication statusPublished - 13 Nov 2021
Event2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition -
Duration: 19 Jun 202125 Jun 2021


Conference2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR


Dive into the research topics of 'Part-aware Panoptic Segmentation'. Together they form a unique fingerprint.

Cite this