Multi3DRefer: Grounding Text Description to Multiple 3D Objects
This addresses a practical need in robotics and real-world applications by enabling flexible object localization, though it is incremental as it extends existing tasks and datasets.
The paper tackles the problem of localizing multiple objects in 3D scenes using natural language descriptions, introducing the Multi3DRefer dataset with 61,926 descriptions for 11,609 objects and a new baseline method that outperforms state-of-the-art on the ScanRefer benchmark.
We introduce the task of localizing a flexible number of objects in real-world 3D scenes using natural language descriptions. Existing 3D visual grounding tasks focus on localizing a unique object given a text description. However, such a strict setting is unnatural as localizing potentially multiple objects is a common need in real-world scenarios and robotic tasks (e.g., visual navigation and object rearrangement). To address this setting we propose Multi3DRefer, generalizing the ScanRefer dataset and task. Our dataset contains 61926 descriptions of 11609 objects, where zero, single or multiple target objects are referenced by each description. We also introduce a new evaluation metric and benchmark methods from prior work to enable further investigation of multi-modal 3D scene understanding. Furthermore, we develop a better baseline leveraging 2D features from CLIP by rendering object proposals online with contrastive learning, which outperforms the state of the art on the ScanRefer benchmark.