Open 3D World in Autonomous Driving

TL;DR

This paper introduces a novel multimodal framework that combines 3D LIDAR point cloud data with textual information to improve open vocabulary object detection in autonomous driving, evaluated on new and existing datasets.

Contribution

It presents an innovative method for fusing 3D point cloud features with textual data to enhance open vocabulary perception in autonomous driving environments.

Findings

Effective fusion of BEV features with textual data improves detection accuracy.

The approach demonstrates strong zero-shot performance on unseen datasets.

The framework advances open vocabulary perception in large-scale 3D outdoor environments.

Abstract

The capability for open vocabulary perception represents a significant advancement in autonomous driving systems, facilitating the comprehension and interpretation of a wide array of textual inputs in real-time. Despite extensive research in open vocabulary tasks within 2D computer vision, the application of such methodologies to 3D environments, particularly within large-scale outdoor contexts, remains relatively underdeveloped. This paper presents a novel approach that integrates 3D point cloud data, acquired from LIDAR sensors, with textual information. The primary focus is on the utilization of textual data to directly localize and identify objects within the autonomous driving context. We introduce an efficient framework for the fusion of bird's-eye view (BEV) region features with textual features, thereby enabling the system to seamlessly adapt to novel textual inputs and enhancing the robustness of open vocabulary detection tasks. The effectiveness of the proposed methodology is rigorously evaluated through extensive experimentation on the newly introduced NuScenes-T dataset, with additional validation of its zero-shot performance on the Lyft Level 5 dataset. This research makes a substantive contribution to the advancement of autonomous driving technologies by leveraging multimodal data to enhance open vocabulary perception in 3D environments, thereby pushing the boundaries of what is achievable in autonomous navigation and perception.