LiPS: Lightweight Panoptic Segmentation for Resource-Constrained Robotics
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911693607534592 |
|---|---|
| author | Galagain, Calvin Poreba, Martyna Goulette, François Stachniss, Cyrill |
| author_facet | Galagain, Calvin Poreba, Martyna Goulette, François Stachniss, Cyrill |
| contents | Panoptic segmentation is a key enabler for robotic perception, as it unifies semantic understanding with object-level reasoning. However, the increasing complexity of state-of-the-art models makes them unsuitable for deployment on resource-constrained platforms such as mobile robots. We propose a novel approach called LiPS that addresses the challenge of efficient-to-compute panoptic segmentation with a lightweight design that retains query-based decoding while introducing a streamlined feature extraction and fusion pathway. It aims at providing a strong panoptic segmentation performance while substantially lowering the computational demands. Evaluations on standard benchmarks demonstrate that LiPS attains accuracy comparable to much heavier baselines, while providing up to 4.5 higher throughput, measured in frames per second, and requiring nearly 6.8 times fewer computations. This efficiency makes LiPS a highly relevant bridge between modern panoptic models and real-world robotic applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00634 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LiPS: Lightweight Panoptic Segmentation for Resource-Constrained Robotics Galagain, Calvin Poreba, Martyna Goulette, François Stachniss, Cyrill Robotics Computer Vision and Pattern Recognition Panoptic segmentation is a key enabler for robotic perception, as it unifies semantic understanding with object-level reasoning. However, the increasing complexity of state-of-the-art models makes them unsuitable for deployment on resource-constrained platforms such as mobile robots. We propose a novel approach called LiPS that addresses the challenge of efficient-to-compute panoptic segmentation with a lightweight design that retains query-based decoding while introducing a streamlined feature extraction and fusion pathway. It aims at providing a strong panoptic segmentation performance while substantially lowering the computational demands. Evaluations on standard benchmarks demonstrate that LiPS attains accuracy comparable to much heavier baselines, while providing up to 4.5 higher throughput, measured in frames per second, and requiring nearly 6.8 times fewer computations. This efficiency makes LiPS a highly relevant bridge between modern panoptic models and real-world robotic applications. |
| title | LiPS: Lightweight Panoptic Segmentation for Resource-Constrained Robotics |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.00634 |