CoLC: Communication-Efficient Collaborative Perception with LiDAR Completion

2026-02-28

AI Summary

This work addresses the challenge of deploying early-fusion cooperative perception systems, which are hindered by high communication overhead. To reduce bandwidth requirements while preserving perceptual complementarity, the authors propose CoLC, a novel framework that introduces LiDAR point cloud completion into early fusion for the first time. CoLC integrates foreground-aware point sampling (FAPS), completion-enhanced early fusion (CEEF), and dense-guided dual alignment (DGDA) to efficiently recover scene completeness under low communication costs. Extensive experiments on both simulated and real-world datasets demonstrate that CoLC achieves a superior trade-off between perception accuracy and communication efficiency, while maintaining robustness in heterogeneous model settings.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Learning & Optimization for CV
• Multiagent Systems: Coordination and Collaboration

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• 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: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Collaborative perception empowers autonomous agents to share complementary information and overcome perception limitations. While early fusion offers more perceptual complementarity and is inherently robust to model heterogeneity, its high communication cost has limited its practical deployment, prompting most existing works to favor intermediate or late fusion. To address this, we propose a communication-efficient early Collaborative perception framework that incorporates LiDAR Completion to restore scene completeness under sparse transmission, dubbed as CoLC. Specifically, the CoLC integrates three complementary designs. First, each neighbor agent applies Foreground-Aware Point Sampling (FAPS) to selectively transmit informative points that retain essential structural and contextual cues under bandwidth constraints. The ego agent then employs Completion-Enhanced Early Fusion (CEEF) to reconstruct dense pillars from the received sparse inputs and adaptively fuse them with its own observations, thereby restoring spatial completeness. Finally, the Dense-Guided Dual Alignment (DGDA) strategy enforces semantic and geometric consistency between the enhanced and dense pillars during training, ensuring consistent and robust feature learning. Experiments on both simulated and real-world datasets demonstrate that CoLC achieves superior perception-communication trade-offs and remains robust under heterogeneous model settings. The code is available at https://github.com/CatOneTwo/CoLC.

Problem

• Collaborative Perception
• Communication Efficiency
• Early Fusion
• LiDAR Completion
• Autonomous Agents

Innovation

• Collaborative Perception
• LiDAR Completion
• Communication Efficiency
• Early Fusion
• Point Sampling