CoopDETR: A Unified Cooperative Perception Framework for 3D Detection via Object Query

TL;DR

CoopDETR introduces a novel cooperative perception framework for autonomous vehicles that uses object-level feature cooperation via object queries, achieving high detection performance with minimal transmission costs.

Contribution

The paper proposes CoopDETR, a new framework that encodes sensor data into object queries and fuses them across agents, reducing bandwidth while maintaining detection accuracy.

Findings

Achieves state-of-the-art detection performance on OPV2V and V2XSet datasets.

Reduces transmission costs to 1/782 of previous methods.

Demonstrates effective object-level cooperation in multi-agent perception.

Abstract

Cooperative perception enhances the individual perception capabilities of autonomous vehicles (AVs) by providing a comprehensive view of the environment. However, balancing perception performance and transmission costs remains a significant challenge. Current approaches that transmit region-level features across agents are limited in interpretability and demand substantial bandwidth, making them unsuitable for practical applications. In this work, we propose CoopDETR, a novel cooperative perception framework that introduces object-level feature cooperation via object query. Our framework consists of two key modules: single-agent query generation, which efficiently encodes raw sensor data into object queries, reducing transmission cost while preserving essential information for detection; and cross-agent query fusion, which includes Spatial Query Matching (SQM) and Object Query Aggregation (OQA) to enable effective interaction between queries. Our experiments on the OPV2V and V2XSet datasets demonstrate that CoopDETR achieves state-of-the-art performance and significantly reduces transmission costs to 1/782 of previous methods.