3EED: Ground Everything Everywhere in 3D
This addresses the need for scalable and diverse 3D grounding benchmarks in outdoor environments for embodied AI research, though it is incremental as it builds on existing work by expanding scale and platform variety.
The paper tackles the problem of visual grounding in 3D for embodied agents by introducing 3EED, a multi-platform, multi-modal benchmark with over 128,000 objects and 22,000 referring expressions, which is 10x larger than existing datasets, and reveals significant performance gaps in evaluations.
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.