VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving

TL;DR

VGGDrive introduces a novel architecture that integrates cross-view 3D geometric grounding into vision-language models, significantly improving autonomous driving tasks by leveraging mature 3D foundation models.

Contribution

The paper proposes VGGDrive, a new architecture with a plug-and-play module that injects 3D geometric features into VLMs for autonomous driving, addressing a key capability gap.

Findings

Enhances VLM performance on five autonomous driving benchmarks

Improves cross-view risk perception, motion prediction, and trajectory planning

Demonstrates the effectiveness of integrating 3D geometric grounding into VLMs

Abstract

The significance of cross-view 3D geometric modeling capabilities for autonomous driving is self-evident, yet existing Vision-Language Models (VLMs) inherently lack this capability, resulting in their mediocre performance. While some promising approaches attempt to mitigate this by constructing Q&A data for auxiliary training, they still fail to fundamentally equip VLMs with the ability to comprehensively handle diverse evaluation protocols. We thus chart a new course, advocating for the infusion of VLMs with the cross-view geometric grounding of mature 3D foundation models, closing this critical capability gap in autonomous driving. In this spirit, we propose a novel architecture, VGGDrive, which empowers Vision-language models with cross-view Geometric Grounding for autonomous Driving. Concretely, to bridge the cross-view 3D geometric features from the frozen visual 3D model with the VLM's 2D visual features, we introduce a plug-and-play Cross-View 3D Geometric Enabler (CVGE). The CVGE decouples the base VLM architecture and effectively empowers the VLM with 3D features through a hierarchical adaptive injection mechanism. Extensive experiments show that VGGDrive enhances base VLM performance across five autonomous driving benchmarks, including tasks like cross-view risk perception, motion prediction, and trajectory planning. It's our belief that mature 3D foundation models can empower autonomous driving tasks through effective integration, and we hope our initial exploration demonstrates the potential of this paradigm to the autonomous driving community.