EffiComm让车辆通信数据量减少60%以上，同时保持顶尖3D检测精度。
EffiComm: Bandwidth Efficient Multi Agent Communication
- 通过动态筛选低价值区域和自适应网格压缩，减少传输数据量
- 在OPV2V上仅用1.5MB/帧即达0.84 [email protected]，优于以往方法
- 适合大规模车联网中高效感知协作，尤其关注带宽受限场景
协同感知使联网车辆能共享传感器信息，克服各自盲区。然而，传输原始点云或完整特征图会严重挤占车对车（V2V）通信带宽，导致延迟与可扩展性问题。我们提出EffiComm，一种端到端框架，传输数据量不足先前方法的40%，同时保持最先进的3D目标检测准确率。EffiComm作用于任意模态的鸟瞰图（BEV）特征图，采用两阶段压缩流程：(1) 选择性传输（ST）利用置信度掩码剔除低效区域；(2) 自适应网格压缩（AGR）通过图神经网络（GNN）根据车辆角色与网络负载分配差异化保留比例。剩余特征经软门控专家混合（MoE）注意力层融合，提升容量与专业化能力以实现高效集成。在OPV2V基准测试中，EffiComm以平均约1.5MB/帧的传输量达到0.84 [email protected]，优于现有方法在准确率-比特曲线上的表现，凸显自适应、学习型通信在可扩展车联网感知中的价值。
原文摘要 · Abstract (English)
Collaborative perception allows connected vehicles to exchange sensor information and overcome each vehicle's blind spots. Yet transmitting raw point clouds or full feature maps overwhelms Vehicle-to-Vehicle (V2V) communications, causing latency and scalability problems. We introduce EffiComm, an end-to-end framework that transmits less than 40% of the data required by prior art while maintaining state-of-the-art 3D object detection accuracy. EffiComm operates on Bird's-Eye-View (BEV) feature maps from any modality and applies a two-stage reduction pipeline: (1) Selective Transmission (ST) prunes low-utility regions with a confidence mask; (2) Adaptive Grid Reduction (AGR) uses a Graph Neural Network (GNN) to assign vehicle-specific keep ratios according to role and network load. The remaining features are fused with a soft-gated Mixture-of-Experts (MoE) attention layer, offering greater capacity and specialization for effective feature integration. On the OPV2V benchmark, EffiComm reaches 0.84 [email protected] while sending only an average of approximately 1.5 MB per frame, outperforming previous methods on the accuracy-per-bit curve. These results highlight the value of adaptive, learned communication for scalable Vehicle-to-Everything (V2X) perception.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。