3D visual grounding aims to identify the target object within a 3D point
cloud scene referred to by a natural language description. While previous works
attempt to exploit the verbo-visual relation with proposed cross-modal
transformers, unstructured natural utterances and scattered objects might lead
to undesirable performances. In this paper, we introduce DOrA, a novel 3D
visual grounding framework with Order-Aware referring. DOrA is designed to
leverage Large Language Models (LLMs) to parse language description, suggesting
a referential order of anchor objects. Such ordered anchor objects allow DOrA
to update visual features and locate the target object during the grounding
process. Experimental results on the NR3D and ScanRefer datasets demonstrate
our superiority in both low-resource and full-data scenarios. In particular,
DOrA surpasses current state-of-the-art frameworks by 9.3% and 7.8% grounding
accuracy under 1% data and 10% data settings, respectively.

DOrA 是一个使用大型语言模型的 3D 视觉指向框架，通过引入有序锚定对象，更新视觉特征并定位目标对象，在低资源和全数据场景下表现出超越当前最先进框架的优越性，分别在 1％数据和 10％数据设置下将基准提高了 9.3％和 7.8％的准确率。