Driving · 2026-11-03
MirrorComm: A Communication-Efficient Cooperative Perception Framework via Mirrored World Models
Shenghan Luo, Yin Xu, Cixiao Zhang, Yang Wang, Yujie Cao, Zhuoran Xiao, Wenjun Zhang
AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.
TL;DR
MirrorComm is a communication-efficient cooperative perception framework using mirrored world models. The receiver predicts the transmitter’s current BEV features from reconstructed history; the transmitter compares this prediction to its current observation and selectively transmits RVQ-encoded updates for positions with large discrepancies. Updated features are fused for downstream detection/segmentation, enabling prediction during communication outages.
Why it matters
The authors aim to reduce communication bandwidth in cooperative perception by avoiding repeated transmission of temporally predictable information. By using synchronized “mirrored” world models at both transmitter and receiver, the method determines what to send from transmitter-side prediction errors (no receiver feedback link), and can continue updating locally during intermittent communication.
Method
- Mirrored world models: receiver predicts transmitter’s current BEV features from four-frame shared reconstructed history; transmitter replicates receiver prediction from synchronized history.
- Prediction-guided selective communication: transmitter computes per-position L2 discrepancy between predicted and current features, selects positions within budget, and transmits their RVQ-encoded observation features plus positions.
- Deterministic feature update: both ends decode received updates and replace predictions at selected positions, then append reconstructed transmitter features to the shared history for subsequent prediction.
Abstract (from arXiv)
Cooperative perception (CP) requires substantial communication bandwidth to exchange sensing information among connected agents. A variety of compression techniques have been proposed to reduce transmission costs while retaining task-relevant information. However, most existing methods follow a frame-wise compression paradigm, overlooking temporal predictability and repeatedly transmitting information that could be inferred from historical context. To address these limitations, we propose MirrorComm, the first world model-based communication-efficient CP framework. Specifically, mirrored world models at the transmitter and receiver predict the transmitter's current observation from a shared history of its reconstructed observations. The transmitter compares this prediction with its current observation and selectively transmits observation updates to correct prediction errors, reducing repeated transmission of predictable information. Experiments on the OPV2V dataset across two downstream tasks including object detection and semantic segmentation show that MirrorComm reduces communication bandwidth requirements by up to approximately 66-fold while maintaining comparable performance to a state-of-the-art (SOTA) method. Ablation studies further demonstrate the effectiveness of the individual components.
Related papers
- Duo: A Reciprocal World Model for Full-Duplex Interaction
- Video2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos
- Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
- Embodied Semantic Communication for Collective Autonomous Agents: A Tutorial on Representation, Wireless Delivery, and Closed-Loop Coordination
- D-World: An Explicit World-Language-Action Model with Recursive Self-Improvement under Dual Control
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: 2026-11-02 · Indexed by Pub-AI: 2026-11-03 UTC
MirrorComm: A Communication-Efficient Cooperative Perception Framework via Mirrored World Models
Preprint posted: 2026-11-02 · Original record ↗
- arxiv
- 2611.02405
Explicit source versions (1)
- v1 · 2026-11-02
- Preprint available
Source date: 2026-11-02 · First detected: 2026-11-03 UTC · Historical baseline
Source evidence (1)
- Official evidence ↗ · atom:published (official metadata)
Abstract · arxiv
Cooperative perception (CP) requires substantial communication bandwidth to exchange sensing information among connected agents. A variety of compression techniques have been proposed to reduce transmission costs while retaining task-relevant information. However, most existing methods follow a frame-wise compression paradigm, overlooking temporal predictability and repeatedly transmitting information that could be inferred from historical context. To address these limitations, we propose MirrorComm, the first world model-based communication-efficient CP framework. Specifically, mirrored world models at the transmitter and receiver predict the transmitter's current observation from a shared history of its reconstructed observations. The transmitter compares this prediction with its current observation and selectively transmits observation updates to correct prediction errors, reducing repeated transmission of predictable information. Experiments on the OPV2V dataset across two downstream tasks including object detection and semantic segmentation show that MirrorComm reduces communication bandwidth requirements by up to approximately 66-fold while maintaining comparable performance to a state-of-the-art (SOTA) method. Ablation studies further demonstrate the effectiveness of the individual components.
