Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene Understanding

Research output: Contribution to journalArticleAcademic

6 Downloads (Pure)

Abstract

In this work, we present two novel datasets for image scene understanding. Both datasets have annotations compatible with panoptic segmentation and additionally they have part-level labels for selected semantic classes. This report describes the format of the two datasets, the annotation protocols, the merging strategies, and presents the datasets statistics. The datasets labels together with code for processing and visualization will be published at https://github.com/tue-mps/panoptic_parts.
Original languageEnglish
Article number2004.07944
Number of pages21
JournalarXiv
Volume2020
Publication statusPublished - 16 Apr 2020

Fingerprint Dive into the research topics of 'Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene Understanding'. Together they form a unique fingerprint.

  • Cite this