通过分布式编码提升车联网协同感知效率，用极少带宽实现高精度3D理解。
V2X-DSC: Multi-Agent Collaborative Perception with Distributed Source Coding Guided Communication
- 利用条件编解码器，仅传输邻居视角的差异信息，减少冗余
- 在千比特级通信下实现领先精度，相比基线提升12.3%平均精度
- 可插入多种感知框架，适合低带宽车联网场景
协同感知通过融合多智能体观测提升3D理解能力，但密集的BEV特征会占用大量车联网链路带宽。我们发现各智能体观察同一物理世界，特征高度相关；因此接收方只需获取本地上下文之外的增量信息。从分布式源编码角度出发，提出V2X-DSC框架，采用条件编解码器（DCC）实现受限带宽下的融合。发送方将BEV特征压缩为紧凑代码，接收方以本地特征作为侧信息进行条件重建，将比特资源分配给互补线索而非重复内容。该结构正则化学习，促进增量表征，生成更少噪声的特征。在DAIR-V2X、OPV2V和V2X-Real数据集上的实验表明，在千比特级通信下达到最优精度-带宽权衡，并可作为即插即用通信模块适配多种融合主干网络。
原文摘要 · Abstract (English)
Collaborative perception improves 3D understanding by fusing multi-agent observations, yet intermediate-feature sharing faces strict bandwidth constraints as dense BEV features saturate V2X links. We observe that collaborators view the same physical world, making their features strongly correlated; thus receivers only need innovation beyond their local context. Revisiting this from a distributed source coding perspective, we propose V2X-DSC, a framework with a Conditional Codec (DCC) for bandwidth-constrained fusion. The sender compresses BEV features into compact codes, while the receiver performs conditional reconstruction using its local features as side information, allocating bits to complementary cues rather than redundant content. This conditional structure regularizes learning, encouraging incremental representation and yielding lower-noise features. Experiments on DAIR-V2X, OPV2V, and V2X-Real demonstrate state-of-the-art accuracy-bandwidth trade-offs under KB-level communication, and generalizes as a plug-and-play communication layer across multiple fusion backbones.
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。