LiPS: Lightweight Panoptic Segmentation for Resource-Constrained Robotics

2026-04-01

AI Summary

This work addresses the challenge of deploying computationally intensive panoptic segmentation models on resource-constrained robotic platforms. The authors propose a lightweight panoptic segmentation method that retains the query-based decoding mechanism while introducing an efficient feature extraction and fusion pathway to substantially reduce computational overhead. By leveraging a streamlined network architecture and an optimized feature processing pipeline, the model achieves accuracy comparable to that of heavyweight counterparts on standard benchmarks, while attaining a 4.5× speedup in inference and reducing computational cost to approximately one-sixth (1/6.8) of the original.

Abstract

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.

Problem

• panoptic segmentation
• resource-constrained robotics
• computational efficiency
• lightweight models
• real-time perception

Innovation

• Lightweight
• Panoptic Segmentation
• Query-based Decoding
• Feature Fusion
• Resource-Constrained Robotics