Scene-Centric Unsupervised Panoptic Segmentation
Abstract
Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In contrast to prior work on unsupervised panoptic scene understanding, we eliminate the need for object-centric training data, enabling the unsupervised understanding of complex scenes. To that end, we present the first unsupervised panoptic method that directly trains on scene-centric imagery. In particular, we propose an approach to obtain high-resolution panoptic pseudo labels on complex scene-centric data, combining visual representations, depth, and motion cues. Utilizing both pseudo-label training and a panoptic self-training strategy yields a novel approach that accurately predicts panoptic segmentation of complex scenes without requiring any human annotations. Our approach significantly improves panoptic quality, e.g., surpassing the recent state of the art in unsupervised panoptic segmentation on Cityscapes by 9.4% points in PQ.
Cite
@article{arxiv.2504.01955,
title = {Scene-Centric Unsupervised Panoptic Segmentation},
author = {Oliver Hahn and Christoph Reich and Nikita Araslanov and Daniel Cremers and Christian Rupprecht and Stefan Roth},
journal= {arXiv preprint arXiv:2504.01955},
year = {2025}
}
Comments
To appear at CVPR 2025. Christoph Reich and Oliver Hahn - both authors contributed equally. Code: https://github.com/visinf/cups Project page: https://visinf.github.io/cups/