CERF: Communication-Efficient and Retraining-Free Collaborative Perception

2026-09-01

AI Summary

为解决协作感知中通信开销大及异构挑战，提出CERF框架，通过引入虚拟模态和使用卡尔曼滤波器等方法减少95%的通信开销并支持无缝集成未知异构代理。

Abstract

Collaborative perception shares information among multiple agents to obtain a comprehensive scene representation, enhancing the perceptual capability of individual agents. However, most existing methods rely on transmitting and fusing dense feature maps for collaboration, which incurs inevitable communication overhead and heterogeneity challenges, limiting their practicality for real-world deployment. To address these challenges, we propose CERF, a novel Communication-Efficient and Retraining-Free framework for open heterogeneous collaborative perception. In CERF, we introduce a new virtual modality (termed Poture), which is generated from the perception outputs of other agents, to augment the extracted Bird's Eye View (BEV) features of the ego agent. To mitigate transmission delays, we employ a Kalman-filter based tracker and a motion forecasting model to derive the current predictions from historical perception results. Extensive experiments demonstrate that CERF achieves performance comparable to mainstream intermediate-collaboration methods while reducing communication overhead by 95% across various downstream tasks. Furthermore, CERF enables seamless integration of unknown heterogeneous agents into the existing collaborative framework without additional retraining costs. Code is available at https://github.com/uestchjw/CERF.

Problem

• collaborative perception
• communication overhead
• heterogeneity challenges

Innovation

• Communication-Efficient
• Retraining-Free
• Virtual Modality (Poture)
• Kalman-filter based tracker
• Motion Forecasting Model