CoCam4D：面向纯视觉自动驾驶的几何感知协作4D感知

中文摘要 AI 辅助

自动驾驶车辆常因遮挡、盲区、传感器探测范围有限及周边环境复杂而存在感知局限。多智能体协作感知（CP）通过让车辆共享感官信息并协同重建场景来应对这些挑战，但纯视觉感知仍受限于与距离相关的单目深度估计的不确定性。我们提出CoCam4D，这是一种显式建模几何不确定性的协作感知贝叶斯框架，它采用基于VGGT的前馈网络生成带关联不确定性估计的3D高斯场景表示，使多个车辆或智能体能高效融合观测结果。通过共享紧凑的高斯基元，一个智能体的可靠观测可降低另一个智能体的深度不确定性，无需激光雷达传感器。为支持实际部署，我们引入动态目标基元（DOPs），这是一种专为高效C-V2X通信设计的35字节紧凑表示。大量实验表明，我们提出的方法始终优于近期纯视觉方法，在OPV2V+上提升11.48%，在DAIR-V2X-C上提升10.62%，证明了基于几何的协作感知在无激光雷达自动驾驶中的潜力。

英文摘要

Autonomous vehicles often suffer from limited perception due to occlusions, blind spots, limited sensor range, and the complex nature of surrounding environments. Multi-agent collaborative perception (CP) addresses these challenges by allowing vehicles to share sensory information and reconstruct the scene cooperatively. However, camera-only perception remains fundamentally limited by the uncertainty of distance-dependent monocular depth estimation. We propose CoCam4D, a Bayesian framework for collaborative perception that explicitly models geometric uncertainty. It uses a VGGT-based feedforward network to generate 3D Gaussian scene representations with associated uncertainty estimates, enabling multiple vehicles or agents to efficiently combine their observations. By sharing compact Gaussian primitives, reliable observations from one agent can reduce the depth uncertainty of another without requiring LiDAR sensors. To support real-world deployment, we introduce Dynamic Object Primitives (DOPs), a compact 35-byte representation designed for efficient C-V2X communication. Extensive experiments show that our proposed method consistently outperforms recent vision-only methods, achieving improvements of 11.48% on OPV2V+ and 10.62% on DAIR-V2X-C, demonstrating the potential of geometrically grounded collaborative perception for LiDAR-free autonomous driving.

发表机构

• University of Petroleum and Energy Studies（石油与能源大学）
• Valeo Brain（法雷奥研究院）
• Indian Statistical Institute（印度统计研究所）

机构由 AI 辅助整理，请以论文原文为准。