CoLC: Communication-Efficient Collaborative Perception with LiDAR Completion

TL;DR

CoLC introduces a communication-efficient early fusion framework for collaborative perception that uses LiDAR completion and selective data transmission to improve scene understanding while reducing bandwidth requirements.

Contribution

It proposes a novel framework combining LiDAR completion with selective point sampling and dual alignment to enhance perception efficiency in collaborative autonomous systems.

Findings

Outperforms existing methods in perception-communication trade-offs

Maintains robustness under heterogeneous model settings

Effective on both simulated and real-world datasets

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.