V2X-PC: Vehicle-to-everything Collaborative Perception via Point Cluster

TL;DR

This paper introduces V2X-PC, a novel vehicle-to-everything collaborative perception framework using point clusters as message units, which improves object feature preservation, long-range collaboration, and structure communication over traditional BEV map methods.

Contribution

The paper proposes a new point cluster representation and a comprehensive framework for collaborative perception that enhances message efficiency and robustness against noise and latency.

Findings

Outperforms state-of-the-art BEV map-based methods on benchmark datasets.

Effectively manages bandwidth and preserves object features during message exchange.

Robust to real-world noise and latency without fine-tuning.

Abstract

The objective of the collaborative vehicle-to-everything perception task is to enhance the individual vehicle's perception capability through message communication among neighboring traffic agents. Previous methods focus on achieving optimal performance within bandwidth limitations and typically adopt BEV maps as the basic collaborative message units. However, we demonstrate that collaboration with dense representations is plagued by object feature destruction during message packing, inefficient message aggregation for long-range collaboration, and implicit structure representation communication. To tackle these issues, we introduce a brand new message unit, namely point cluster, designed to represent the scene sparsely with a combination of low-level structure information and high-level semantic information. The point cluster inherently preserves object information while packing messages, with weak relevance to the collaboration range, and supports explicit structure modeling. Building upon this representation, we propose a novel framework V2X-PC for collaborative perception. This framework includes a Point Cluster Packing (PCP) module to keep object feature and manage bandwidth through the manipulation of cluster point numbers. As for effective message aggregation, we propose a Point Cluster Aggregation (PCA) module to match and merge point clusters associated with the same object. To further handle time latency and pose errors encountered in real-world scenarios, we propose parameter-free solutions that can adapt to different noisy levels without finetuning. Experiments on two widely recognized collaborative perception benchmarks showcase the superior performance of our method compared to the previous state-of-the-art approaches relying on BEV maps.