WhisperNet：一种可扩展的带宽高效协同感知方案
WhisperNet: A Scalable Solution for Bandwidth-Efficient Collaboration
提出以接收端为中心的全局协调范式，通过轻量显著性元数据与全局请求计划动态分配带宽，并设计协同特征路由模块对齐消息，可即插即用地提升现有协同感知模型的通信效率与鲁棒性。
原文依据 WhisperNet achieves state-of-the-art performance, improving AP@0.7 on OPV2V by 2.4% with only 0.5% of the communication cost.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论协同感知对自动驾驶至关重要，但仍受限于紧张的通信预算。先前工作通过固定速率编码器压缩完整特征图来降低带宽，但这种方法对变化环境的适应性较差；后续发展为空间选择方法，通过聚焦显著区域提升效率，但这种以对象为中心的方法往往牺牲全局上下文，削弱整体场景理解。为克服这些局限，我们提出WhisperNet，一种带宽感知框架，提出了一种新颖的、以接收端为中心的范式，用于智能体间的全局协调。发送端生成轻量级显著性元数据，接收端则制定全局请求计划，动态地为各智能体和特征分配预算，仅检索最具信息量的特征。随后，协同特征路由模块在融合前对齐相关消息，以确保结构一致性。大量实验表明，WhisperNet达到最优性能，在OPV2V上以仅0.5%的通信成本将AP@0.7提升2.4%。作为一个即插即用组件，它仅用5%的全带宽即可提升强基线，并在定位噪声下保持鲁棒性。这些结果表明，在共享什么和在哪里共享上进行全局协调分配，是实现高效协同感知的关键。
英文原文摘要 1431 字符
Collaborative perception is vital for autonomous driving yet remains constrained by tight communication budgets. Earlier work reduced bandwidth by compressing full feature maps with fixed-rate encoders, which adapts poorly to a changing environment, and it further evolved into spatial selection methods that improve efficiency by focusing on salient regions, but this object-centric approach often sacrifices global context, weakening holistic scene understanding. To overcome these limitations, we introduce WhisperNet, a bandwidth-aware framework that proposes a novel, receiver-centric paradigm for global coordination across agents. Senders generate lightweight saliency metadata, while the receiver formulates a global request plan that dynamically budgets feature contributions across agents and features, retrieving only the most informative features. A collaborative feature routing module then aligns related messages before fusion to ensure structural consistency.Extensive experiments show that WhisperNet achieves state-of-the-art performance, improving AP@0.7 on OPV2V by 2.4% with only 0.5% of the communication cost. As a plug-and-play component, it boosts strong baselines with merely 5% of full bandwidth while maintaining robustness under localization noise. These results demonstrate that globally-coordinated allocation across what and where to share is the key to achieving efficient collaborative perception.