V2X-DSC: Multi-Agent Collaborative Perception with Distributed Source Coding Guided Communication

TL;DR

This paper introduces V2X-DSC, a novel distributed source coding framework for multi-agent collaborative perception that efficiently compresses shared features, enabling high-accuracy 3D understanding under strict bandwidth constraints.

Contribution

It proposes a conditional codec approach that compresses features into compact codes and uses local features as side information for reconstruction, improving bandwidth efficiency and perception accuracy.

Findings

Achieves state-of-the-art accuracy-bandwidth trade-offs on multiple datasets.

Demonstrates effective generalization as a plug-and-play communication layer.

Reduces redundant information in feature sharing, improving perception quality.

Abstract

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.