Part-Aware Panoptic Segmentation

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

CVPR 2021 pp. 5485-5494

doi:10.1109/CVPR46437.2021.00544 /cvpr/2021/degeus2021cvpr-partaware/

Abstract

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.

PDF CVPR Semantic Scholar

Cite

Text

de Geus et al. "Part-Aware Panoptic Segmentation." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.00544

Markdown

[de Geus et al. "Part-Aware Panoptic Segmentation." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/degeus2021cvpr-partaware/) doi:10.1109/CVPR46437.2021.00544

BibTeX

@inproceedings{degeus2021cvpr-partaware,
  title     = {{Part-Aware Panoptic Segmentation}},
  author    = {de Geus, Daan and Meletis, Panagiotis and Lu, Chenyang and Wen, Xiaoxiao and Dubbelman, Gijs},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2021},
  pages     = {5485-5494},
  doi       = {10.1109/CVPR46437.2021.00544},
  url       = {https://mlanthology.org/cvpr/2021/degeus2021cvpr-partaware/}
}