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

2026-01-31

AI Summary

This work addresses the challenge of limited V2X communication bandwidth in multi-agent cooperative perception, where transmitting dense BEV features is costly. To this end, it introduces distributed source coding to this domain for the first time and proposes a Distributed Conditional Codec (DCC). In DCC, the sender compresses BEV features, while the receiver leverages its local observations as side information to conditionally reconstruct the features, transmitting only complementary information to drastically reduce communication overhead. This approach enables low-redundancy, high-efficiency feature sharing and enhances the quality of reconstructed features. Experiments on DAIR-V2X, OPV2V, and V2X-Real datasets demonstrate that DCC achieves state-of-the-art accuracy–bandwidth trade-offs under kilobyte-level communication budgets and functions as a plug-and-play module compatible with various fusion backbone networks.

Technology Category

• Computer Vision: Multi-modal Vision
• Multiagent Systems: Agent Communication
• Search and Optimization: Distributed Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Collaborative Perception
• Bandwidth Constraint
• V2X Communication
• BEV Features
• Multi-Agent

Innovation

• Distributed Source Coding
• Conditional Codec
• Collaborative Perception
• Bandwidth-Efficient Communication
• BEV Feature Compression