Send Less, Perceive More: Masked Quantized Point Cloud Communication for Loss-Tolerant Collaborative Perception

2026-02-25

AI Summary

This work addresses the challenge of achieving both high accuracy and robustness in collaborative perception under bandwidth constraints and communication packet loss. To this end, we propose QPoint2Comm, a novel framework that integrates quantized point cloud index communication with mask training for the first time. By leveraging a shared codebook to directly transmit indices, our approach significantly improves bandwidth efficiency, while mask training simulates packet loss during training to enhance robustness. Furthermore, we design a cascaded attention fusion module to effectively aggregate multi-vehicle perception features. Extensive experiments demonstrate that our method achieves state-of-the-art performance on both simulated and real-world datasets, substantially outperforming existing approaches in communication efficiency, perception accuracy, and resilience to packet loss.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Multiagent Systems: Agent Communication

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Collaborative perception allows connected vehicles to overcome occlusions and limited viewpoints by sharing sensory information. However, existing approaches struggle to achieve high accuracy under strict bandwidth constraints and remain highly vulnerable to random transmission packet loss. We introduce QPoint2Comm, a quantized point-cloud communication framework that dramatically reduces bandwidth while preserving high-fidelity 3D information. Instead of transmitting intermediate features, QPoint2Comm directly communicates quantized point-cloud indices using a shared codebook, enabling efficient reconstruction with lower bandwidth than feature-based methods. To ensure robustness to possible communication packet loss, we employ a masked training strategy that simulates random packet loss, allowing the model to maintain strong performance even under severe transmission failures. In addition, a cascade attention fusion module is proposed to enhance multi-vehicle information integration. Extensive experiments on both simulated and real-world datasets demonstrate that QPoint2Comm sets a new state of the art in accuracy, communication efficiency, and resilience to packet loss.

Problem

• collaborative perception
• bandwidth constraints
• packet loss
• point cloud communication
• loss-tolerant

Innovation

• quantized point cloud
• masked training
• collaborative perception
• communication efficiency
• packet loss robustness