---
license: mit
---

# Task-Aligned Part-aware Panoptic Segmentation (TAPPS)

[[Paper](https://openaccess.thecvf.com/content/CVPR2024/papers/de_Geus_Task-aligned_Part-aware_Panoptic_Segmentation_through_Joint_Object-Part_Representations_CVPR_2024_paper.pdf)] [[Project page](http://tue-mps.github.io/tapps)] [[Code](https://github.com/tue-mps/tapps/)]

We provide the models for the part-aware panoptic segmentation task, as presented in our CVPR 2024 paper: [Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations](https://openaccess.thecvf.com/content/CVPR2024/papers/de_Geus_Task-aligned_Part-aware_Panoptic_Segmentation_through_Joint_Object-Part_Representations_CVPR_2024_paper.pdf).

For the code, see [https://github.com/tue-mps/tapps/](https://github.com/tue-mps/tapps/).

Please consider citing our work if it is useful for your research.

```
@inproceedings{degeus2024tapps,
  title={{Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations}},
  author={{de Geus}, Daan and Dubbelman, Gijs},
  booktitle={IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2024}
}
```