3EED: Ground Everything Everywhere in 3D

TL;DR

3EED introduces a large-scale, multi-platform 3D grounding benchmark with diverse outdoor scenes, enabling research on generalizable language grounding for embodied agents across various outdoor environments.

Contribution

We present 3EED, a comprehensive outdoor 3D grounding dataset and benchmark with novel platform-aware normalization and cross-modal alignment techniques.

Findings

Significant performance gaps across platforms highlight challenges in generalizable 3D grounding.

The dataset contains over 128,000 objects and 22,000 referring expressions, 10x larger than prior datasets.

Benchmark protocols facilitate in-domain and cross-platform evaluation.

Abstract

Visual grounding in 3D is the key for embodied agents to localize language-referred objects in open-world environments. However, existing benchmarks are limited to indoor focus, single-platform constraints, and small scale. We introduce 3EED, a multi-platform, multi-modal 3D grounding benchmark featuring RGB and LiDAR data from vehicle, drone, and quadruped platforms. We provide over 128,000 objects and 22,000 validated referring expressions across diverse outdoor scenes -- 10x larger than existing datasets. We develop a scalable annotation pipeline combining vision-language model prompting with human verification to ensure high-quality spatial grounding. To support cross-platform learning, we propose platform-aware normalization and cross-modal alignment techniques, and establish benchmark protocols for in-domain and cross-platform evaluations. Our findings reveal significant performance gaps, highlighting the challenges and opportunities of generalizable 3D grounding. The 3EED dataset and benchmark toolkit are released to advance future research in language-driven 3D embodied perception.